Image adjust method and image adjust device

Abstract

An image adjustment method includes the following steps: capturing an image using an image capturing device; detecting a plurality of gestures in the image using a processor; identifying a gesture area formed by the plurality of gestures using the processor, thereby generating a first correction area in the image based on the gesture area; and adjusting the image based on the first correction area using the processor to generate the adjusted image.

Description

Image adjustment method and image adjustment device This case relates to an image processing method and apparatus. More specifically, this case relates to an image adjustment method and an image adjustment apparatus. The demand for video conferencing and web conferencing is gradually increasing. When recording or streaming with a camera, objects or documents that are originally square will appear as perspective distortion on the screen due to the camera's angle. Current image correction methods are not easy for users to operate, or the corrected image may not match the user's desired range and angle. Therefore, the above-mentioned technologies still have many shortcomings, and practitioners in this field need to develop other suitable image adjustment methods. One aspect of this case relates to an image adjustment method. The image adjustment method includes the following steps: capturing an image using an image capturing device; detecting a plurality of gestures in the image using a processor; identifying a gesture area formed by the plurality of gestures using the processor, thereby generating a first correction area in the image based on the gesture area; and adjusting the image using the processor based on the first correction area to generate the adjusted image. Another aspect of this case relates to an image adjustment device. The image adjustment device includes a data splitter, a first processor, and a second processor. The data splitter receives images from an image capturing device. The data splitter outputs a first image and a second image based on the images. The first processor is coupled to the data splitter. The first processor detects a plurality of gestures of objects and targets in the first image. The first processor identifies a gesture area formed by the plurality of gestures, thereby outputting a first signal and a second signal. The second processor is coupled to the data splitter and the processor. The second processor receives the second image, the first signal, and the second signal. The second processor forms a correction area in the second image based on the first signal and the gesture area. The second processor adjusts the objects in the second image based on the second signal and the correction area, thereby outputting the adjusted second image to an image output device. The spirit of this case will be clearly explained below with diagrams and detailed description. Anyone with ordinary knowledge in the relevant technical field can make changes and modifications based on the technology taught in this case after understanding the embodiments of this case, without departing from the spirit and scope of this case. The terminology used herein is for the purpose of describing specific embodiments only and is not intended to limit the scope of this case. Singular forms such as “a,” “this,” “this,” “the,” and “the” as used herein also include plural forms. The terms "include", "include", "have", "contain", etc., used in this article are all open-ended terms, meaning they include but are not limited to. Unless otherwise specified, the terms used herein generally have their ordinary meaning in the context of this field, the subject matter, and the specific content of this case. Certain terms used to describe this case will be discussed below or elsewhere in this specification to provide additional guidance to those skilled in the art in describing this case. Figure 1 is a block diagram illustrating an image adjustment device 100 according to some embodiments of this invention. In some embodiments, referring to Figure 1, the image adjustment device 100 includes a data splitter 110, a first processor 120, and a second processor 130. The image adjustment device 100 is coupled to an image capturing device 700 and an image output device 900. In some embodiments, the image capturing device 700 may be a document scanning device, a document camera, a video camera, a mobile device, etc., without limitation. In some embodiments, the image output device 900 may be, for example, a display, a computer screen, or a mobile device, without limitation. The second processor 130 is coupled to the data splitter 110 and the first processor 120. In some embodiments, the second processor 130 includes an image processor. In some embodiments, referring to Figure 1, the data splitter 110 is used to receive an image from the image capturing device 700. In this embodiment, an image is used as an example, but it is not limited thereto. In some embodiments, the image capturing device 700 may be an image capturing device with multiple lenses, such as a dual-lens camera, a multi-lens camera, or a document camera. The data splitter 110 is used to receive images captured by at least one of the multiple lenses. The data splitter 110 outputs a first image and a second image based on the received images. The first image and the second image are the same scene. The purpose of setting up the data splitter is to avoid the image adjustment device 100 taking too long to recognize gestures in the image, which would cause a delay in image output. In some embodiments, the first processor 120 is used to receive the first image. The first processor 120 is used to identify a gesture area formed by a plurality of gestures, thereby outputting a first signal S1 and a second signal S2 to the second processor 130. In some embodiments, the first processor 120 is further configured to detect objects and a plurality of gestures (e.g., a plurality of hand gestures of a target object) in the first image, and to identify whether the plurality of gestures overlap with the perspective distortion outline of the object. If the plurality of gestures overlap with the perspective distortion outline, the first processor 120 outputs a first signal S1 and a second signal S2 to the second processor 130. In some embodiments, the first processor 120 includes a gesture recognition unit 121 and a gesture shaping unit 122. In some embodiments, the target object may be a human or a laboratory animal. It should be noted that the process by which the first processor 120 detects the object and the plurality of gestures of the target object will be described in detail later. In some embodiments, the gesture recognition unit and the gesture shaping unit may be constructed of hardware or software, and are not limited herein. In some embodiments, the gesture recognition unit 121 is used to recognize a plurality of gestures and the perspective deformation contours of objects, so as to simultaneously output a first signal S1 to the second processor 130 and the gesture shaping unit 122. In some embodiments, the gesture shaping unit 122 is used to identify whether a plurality of gestures have been held for a gesture shaping time based on the first signal S1, and outputs a second signal S2 to the second processor 130. In some embodiments, the first signal S1 and the second signal S2 include image coordinate information and / or image information of the gesture. In some embodiments, the gesture shaping time is approximately 3 seconds. It should be noted that the gesture shaping time can be designed according to actual needs and is not limited to the embodiments described in this case. In some embodiments, referring to Figure 1, the second processor 130 is used to receive the second image. The second processor 130 is used to form a correction region in the second image based on the first signal S1 and the gesture region. The second processor 130 is used to adjust the second image based on the second signal S2 and the correction region, thereby outputting the adjusted second image to the image output device 900. In some embodiments, the second processor 130 is further configured to draw a plurality of bounding points in the second image according to the first signal S1. The second processor 130 is further configured to adjust objects in the second image according to the second signal S2. In some embodiments, the second processor 130 includes a drawing unit 131 and an image correction unit 132. It should be noted that the process by which the second processor 130 draws a plurality of bounding points according to the first signal S1 will be described in detail later. In some embodiments, the drawing unit and the image correction unit can be constructed of hardware or software, and there is no limitation herein. In some embodiments, the drawing unit 131 is used to draw a plurality of selection points in the second image according to the first signal S1. If the drawing unit 131 does not receive the first signal S1 and / or the second signal S2, the drawing unit 131 directly outputs the second image to the image correction unit 132. The image correction unit 132 directly outputs the second image to the image output device 900. At this time, the second image is the original image captured by the image capturing device 700. If the drawing unit 131 receives the first signal S1 but does not receive the second signal S2, the drawing unit 131 draws the current second image according to the selection points, and outputs it to the image correction unit 132. The image correction unit 132 outputs the current second image to the image output device 900. In some embodiments, the image correction unit 132 adjusts the objects in the second image according to the second signal S2. In some embodiments, the image correction unit 132 adjusts the objects in the second image in a manner that includes correcting the perspective distortion contours of the objects in the trapezoidal correction image. Figure 2A is a schematic diagram illustrating gesture recognition types according to some embodiments of this invention. In some embodiments, please refer to Figure 1 and Figure 2A. Figure 2A shows the image captured by the image capturing device 700, processed by the image adjustment device 100, and finally presented by the image output device 900. In some embodiments, please refer to Figure 2A. The first processor 120 is used to identify the gesture area A1 formed by gestures (e.g., left hand gesture G1 and right hand gesture G2 of the target object) in the image I. In some embodiments, regardless of whether there is an object O in the image I, the image adjustment device 100 can directly use the gesture area A1 as the correction area and adjust the image I according to the correction area. In some embodiments, referring to Figure 2A, the first processor 120 is further used to identify the object O and gestures (e.g., the left hand gesture G1 and the right hand gesture G2 of the target object) in the image I. The left hand gesture G1 is exemplified by raising the thumb and index finger. The right hand gesture G2 is also exemplified by raising the thumb and index finger. It should be noted that the type of gesture identified is raising two fingers of each hand respectively. The type and number of fingers are not limited to the illustrated embodiment. The image adjustment device 100 of this invention draws the gesture area A1 based on the finger positions shown in Figure 2A. Figure 2B is a schematic diagram illustrating gesture recognition types according to some embodiments of this invention. In some embodiments, referring to Figure 2B, compared to Figure 2A, the left-hand gesture G3 in the image is a two-finger gesture. The right-hand gesture G4 is changed to a single-finger gesture. The image adjustment device 100 of this invention will draw the gesture area A2 as shown in Figure 2B based on the finger position. Figure 2C is a schematic diagram illustrating gesture recognition types according to some embodiments of this invention. In some embodiments, please refer to Figure 2C. Compared to Figure 2A, left-hand gesture G5 and left-hand gesture G6 are both changed to single-finger gestures. Right-hand gesture G4 is changed to a single-finger gesture. The image adjustment device 100 of this invention will draw the gesture area A3 as shown in Figure 2C according to the finger position. It should be noted that the gesture area A1 in Figure 2A, the gesture area A2 in Figure 2B, and the gesture area A3 in Figure 2C are all extended and connected along the X-axis and Y-axis directions in the image according to the finger position to form gesture areas. It should be noted that the image adjustment system 100 of this invention is mainly used to recognize gestures as shown in Figure 2A, but is not limited to the embodiments of this invention. It should be noted that the perspective distortion outline of the aforementioned objects is essentially the shape of the object distortion in the image caused by the lens of the image capturing device. In practice, perspective distortion refers to the phenomenon where, when shooting videos and photographs, the relative proportions of an object and its surrounding area are completely different from those seen through the lens of the image capturing device. Due to the change in the relative proportions of near and far features, objects bend or distort as shown in Figures 2A to 2C. Perspective distortion is determined by the relative distance between the object captured by the image capturing device and the object being viewed. The purpose of this case is to correct perspective distortion of objects in images in real time by recognizing gestures. Please refer to Figures 3 through 6B. Figure 3 is a schematic diagram illustrating the steps of the correction process of the image adjustment method 300 according to some embodiments of this invention. Figures 4A through 6B are schematic diagrams of images according to some embodiments of this invention. In some embodiments, this image adjustment method 300 may be performed by the image adjustment system 100 shown in Figure 1. The image adjustment method 300 includes the steps described below. In step 310, an image is captured. In this embodiment, an image is used as an example, but this is not a limitation. In some embodiments, please refer to Figures 1, 3, and 4A. In situations such as video conferencing, live streaming, or distance learning, the image capturing device 700 captures image I1 as shown in Figure 4A. Image I1 contains a perspective-distorted object O1. In this embodiment, object O1 is exemplified as a document, but the outline of the object is not limited to the illustrated embodiment. The image adjustment device 100 continuously captures images of the foreground environment through the lens of the image capturing device 700. In step 320, gestures are detected. In some embodiments, please refer to Figures 1, 2A, 3, and 4B. Following the steps described above, the gesture recognition unit 121 of the image adjustment system 100 detects multiple gestures of the object O1 and the target object in the image I2 (e.g., left-hand gesture G1 and right-hand gesture G2 as shown in Figure 2A). If the image adjustment system 100 detects multiple gestures of the object O1 and the target object, it will execute the subsequent step 330. If the image adjustment system 100 does not detect multiple gestures of the object O1 and the target object, it will repeat step 320. It should be noted that the gesture recognition time is approximately 10 to 20 milliseconds (ms), and is not limited to the embodiments described herein. In step 330, the finger position is identified to form a plurality of selection points. In some embodiments, please refer to Figures 1, 2A, 3, and 4B. Following the above steps, the finger position of the gesture intersects with the perspective distortion outline of object O1 at selection points F1, F2, F3, and F4, respectively. At this time, the gesture recognition unit 121 of the image adjustment system 100 outputs a first signal S1 to the drawing unit 131. The drawing unit 131 draws selection points F1 to F4 on image I2 according to the first signal S1. Selection points F1 to F4 are connected to form a first correction area. In step 340, finger movement of the gesture is detected. In some embodiments, please refer to Figures 1, 2A, 3 to 6A. Since the range formed by the open hand gesture of the target object may not match the size of the object O1, two situations will arise. This image adjustment method will adjust the image according to the two situations. In some embodiments, referring to Figures 1, 4B to 5B, the first case is that the area formed by the outstretched hand gesture of the target object (i.e., the first correction area formed by the selection points F1 to F4, i.e., the halftone marking area) roughly matches the size of the object O1. Therefore, the gesture does not need to be moved. The image adjustment system 100 of this invention detects whether the positions of the plurality of fingers move outside the first correction area according to the plurality of first selection points. If the positions of the plurality of fingers do not move outside the first correction area, the image adjustment system 100 of this invention will directly execute steps 360 and 370 to adjust the image I2 according to the first correction area. In detail, the gesture shaping unit 122 of the image adjustment system 100 detects that the gesture has not moved and maintains and holds the gesture for a certain period of time (e.g., the gesture shaping time is about three seconds). The gesture shaping unit 122 will output a second signal S2 to the drawing unit 131 and the image correction unit 132 to execute steps 360 and 370. In some embodiments, referring to Figures 1 and 6A, the second case is that the area formed by the open gesture of the target object (i.e., the first correction area formed by selection points F1 to F4, i.e., the dot marking area) cannot cover object O1. Therefore, the target object can first form selection points F1 to F4 by the finger positions of the perspective distortion outline of object O2 in image I5 using gestures. The image adjustment system 100 of this invention detects whether the positions of a plurality of fingers move outside the first correction area (dot marking area) according to the plurality of first selection points. If the positions of the plurality of fingers move outside the first correction area (e.g., the area formed by selection points F1 to F4), the image adjustment system 100 of this invention performs subsequent step 350. In detail, the gesture recognition unit 121 of the first processor 120 of the image adjustment system 100 outputs a first signal S1 to the second processor 130 to draw selection points F1 to F4. In some embodiments, the gesture recognition unit 121 of the first processor 120 is further used to roughly identify whether the first correction area covers the object O2. The drawing unit 131 of the second processor 130 is further used to draw different types of selection points based on the object O2, the first correction area, and the gesture. In step 350, the selection points are moved. In some embodiments, referring to Figures 1, 3, and 6B, following the second case described in step 340 above, the image adjustment system 100 identifies that a plurality of finger positions have moved outside the first correction area (e.g., the area formed by selection points F1 to F4) to form a second correction area (e.g., the area formed by selection points P1 to P4), thereby making the second correction area cover the object O2. The image adjustment system 100 adjusts the image I6 according to the first correction area and / or the second correction area. In detail, the gesture recognition unit 121 of the first processor 120 of the image adjustment system 100 is further used to roughly identify whether the first correction area and / or the second correction area cover the object O2, so as to output a third signal to the drawing unit 131. The drawing unit 131 temporarily records the frame selection points F1 to F4 on the image I6 according to the third signal. The gesture recognition unit 121 identifies that the positions of a plurality of fingers move from the frame selection points F1 to F4 to the frame selection points P1 to P4 respectively. It should be noted that at this time, the gesture can be maintained as shown in Figure 2A or changed to the gesture shown in Figure 2B or the gesture shown in Figure 2C for movement. After the finger positions of the gesture are maintained and held at the frame selection points P1 to P4 for a gesture fixation time (for example, the gesture fixation time is about three seconds), the image adjustment system 100 will execute the subsequent steps 360 and 370. It should be noted that the difference between the second signal S2 and the third signal is that the second signal S2 is the signal output after the finger position of the gesture has been fixed for a certain period of time. The third signal corresponds to the signal continuously output as the finger position of the gesture changes. In step 360, a correction area is generated based on the selected points. In some embodiments, please refer to Figures 1 and 4B. As described in step 340 above, the drawing unit 131 of the image adjustment system 100 of this invention forms a first correction area based on the selected points F1 to F4. In some embodiments, please refer to Figure 1 and Figure 6B. As described in step 350 above, in the second case, the drawing unit 131 of the image adjustment system 100 of this invention forms a second correction area based on the selected points P1 to P4. In step 370, the image is adjusted according to the correction area. In some embodiments, please refer to Figures 1, 4B, 5A and 5B. Following the first case described in step 360 above, the image correction unit 132 of the image adjustment system 100 corrects image I2 into image I3 as shown in Figure 5A or image I4 as shown in Figure 5B based on the second signal S2 and the first correction area. In some embodiments, please refer to Figures 1, 5A, 5B and 6B. Following the second case described in step 360 above, the image correction unit 132 of the image adjustment system 100 corrects image I6 to image I3 as shown in Figure 5A or image I4 as shown in Figure 5B based on the second signal S2, the first correction area and / or the second correction area. It should be noted that the difference between images I3 and I4 depends on the size of the area of ​​object O1 that the target object intends to select via gesture. Therefore, the area of ​​object O1 to be selected will be corrected to object O' in Figure 5A or object O1' in Figure 5B. In other words, the size of the first correction area formed by selection points F1 to F4 or the size of the second correction area formed by selection points P1 to P4 will affect the image adjustment. Object O' and object O1' are the corrected contours of the perspective distortion contours of the aforementioned object O. In some embodiments, for the sake of understanding the flow of the image adjustment method 700 of this invention, please refer to Figures 7 to 9. Figure 7 is a schematic flowchart illustrating the selection process of the image adjustment method 700 according to other embodiments of this invention. Figures 7 to 9 are schematic diagrams of images according to some embodiments of this invention. In some embodiments, this image adjustment method 700 can be performed by the image adjustment system 100 shown in Figure 1. The image adjustment method 700 is a selection method for a portion of the selected image after the correction process of the image adjustment method 300 of Figure 3 above. The image adjustment method 700 includes the steps described below. In step 710, an adjusted image is captured. In this embodiment, an image is used as an example, but it is not limited thereto. In some embodiments, please refer to Figures 1, 5A, 5B, and 7. In the case of video conferencing, live streaming, or distance learning, the image has been corrected to image I3 as shown in Figure 5A or image I4 as shown in Figure 5B. In some embodiments, step 710 may also capture an unadjusted image. In step 720, a gesture is detected. In some embodiments, please refer to Figures 1, 2A to 2B and 7, the image adjustment system 100 of this invention detects whether the gesture of the target object is as shown in Figure 2A or as shown in Figure 2B. In step 730, the wrist of the gesture is detected. In some embodiments, please refer to Figures 1, 7, and 8A. The image adjustment system 100 of this invention detects whether the image I7 contains the positions of the fingers of both hands (e.g., the finger positions F5 and F6 of the target object) and the wrist position W1. If the image adjustment system 100 detects the wrist, the image adjustment system 100 executes step 740. If the image adjustment system 100 does not detect the wrist, the image adjustment system 100 executes step 741. It should be noted that the purpose of the image adjustment method 700 in this invention to detect the wrist is to enable the target object to write or enlarge the content of the document when it is conducting video conferencing, live streaming, or distance learning, so as to provide the content of the object to the meeting participants in real time for discussion or recording. When the target object adopts a writing posture, the wrist of the dominant hand holding the pen is placed on the object, and the fingers of the other hand are used as an aid. It should be noted that the positional data of the first correction area, after being adjusted by the image adjustment method 300 described above, is still stored in the image adjustment device 100 of this invention. In practice, the relative distance between the image capturing device 700 and the actual object remains unchanged. Both the image adjustment method 300 and the image adjustment method 700 of this invention involve changes made after image processing. In step 740, the finger positions and wrist positions are identified to form a plurality of first selection points. In some embodiments, referring to Figures 1, 7, and 8A, the image adjustment system 100 of this invention detects the wrist position W1 of the hand gesture of the target object in image I7, which includes finger positions (e.g., finger positions F5 and F6). The identification of the wrist position by the image adjustment system 100 of this invention is similar to the identification of the finger positions in Figure 2B. Therefore, the image adjustment system 100 of this invention identifies the finger positions and wrist positions in a first correction area to form a plurality of first selection points. The plurality of first selection points are finger positions F5, finger positions F6, and wrist position W1. In step 741, finger positions are identified to form a plurality of second selection points. In some embodiments, referring to Figures 1, 7, and 9, the image adjustment system 100 of this invention does not identify the wrist in image I9. The image adjustment system 100 of this invention identifies finger positions in a first correction area to form a plurality of second selection points. The second selection points are finger positions F5 and F6. In step 750, a selection area is generated based on the first selection point or the second selection point. In some embodiments, please refer to Figures 1, 7 and 8A. Following the steps described above, the image adjustment system 100 of this invention generates a selection area SA1 based on a plurality of first selection points (i.e., finger position F5, finger position F6 and wrist position W1). In some embodiments, referring to Figures 1, 7, and 9, following the steps described above, the image adjustment system 100 of this invention forms a boundary L2 based on finger positions F5 and F6. The image adjustment system 100 of this invention forms two parallel lines (e.g., parallel lines PL1 and PL2) along the X-axis based on the boundary L2 and the first correction area. These two parallel lines intersect with the outline of object O' (e.g., the boundary L1 of object O' in image I9), thereby forming a second selection area SA2. In step 760, the image is processed based on the selected area image. In some embodiments, referring to Figures 1, 7, 8A, and 8B, the image adjustment system 100 of this invention processes image I7 into image I8 based on a first selected region SA1. More specifically, the image adjustment system 100 enlarges image I7 proportionally based on a second selected region SA2 to obtain image I8. In some embodiments, referring to Figures 1, 7, 8B, and 9, the image adjustment system 100 of this invention generates a selection region SA2 based on a plurality of first selection points (i.e., finger positions F5 and F6), and performs image processing on image I9 to obtain image I8 based on the second selection region SA2. Specifically, the image adjustment system 100 of this invention enlarges image I9 proportionally to obtain image I8 based on the second selection region SA2. It should be noted that if finger position F5 and finger position F6 are on the left and right sides respectively, the image adjustment system 100 of this case will take the finger position closest to the center C1 of object O' as the reference, extend the boundary L2 vertically along the Y-axis, and intersect with the parallel lines PL1 and PL2 extending from finger position F5 and finger position F6. Based on the foregoing embodiments, this invention provides an image adjustment method and an image adjustment device. The image adjustment method of this invention enables users to quickly and accurately select the range of objects in scenarios such as video conferencing, live streaming, or distance learning, without going through a complicated adjustment process. Although detailed embodiments have been disclosed above, this application does not exclude other possible implementations. Therefore, the scope of protection of this application shall be determined by the appended claims and not by the foregoing embodiments. For those skilled in the art, various modifications and refinements can be made to this case without departing from its spirit and scope. Based on the foregoing embodiments, all modifications and refinements made to this case are also covered within the protection scope of this case. 100: Image adjustment device; 110: Data splitter; 120: First processor; 121: Gesture recognition unit; 122: Gesture shaping unit; 130: Second processor; 131: Drawing unit; 132: Image correction unit; 700: Image capturing device; 900: Image output device; S1: First signal; S2: Second signal; I, I1~I9: Image; O, O1, O2, O', O1': Object; A1~A3: Gesture area; G1~G6: Gesture; 300: Method; 310~370: Step; F1~F4: Selection point; P1~P4: Selection point; 700: Method; 710~760: Step; F5~F6: Finger position; W1: Wrist position; SA1~SA2: Selection area; C1: Center of object; PL1~PL2: Parallel line; L1: Boundary of object; L2: Boundary; X, Y: Coordinate axis direction. The contents of this application can be better understood by referring to the embodiments described in the following paragraphs and the following figures: Figure 1 is a block diagram illustrating an image adjustment device according to some embodiments of this application; Figure 2A is a diagram illustrating gesture recognition types according to some embodiments of this application; Figure 2B is a diagram illustrating gesture recognition types according to some embodiments of this application; Figure 2C is a diagram illustrating gesture recognition types according to some embodiments of this application; Figure 3 is a step diagram illustrating the correction process of an image adjustment method according to some embodiments of this application; Figure 4A is an image illustration according to some embodiments of this application; Figure 4B is an image illustration according to some embodiments of this application; Figure 5A is an image illustration according to some embodiments of this application; Figure 5B is an image illustration according to some embodiments of this application; Figure 6A is an image illustration according to some embodiments of this application; Figure 6B is an image illustration according to some embodiments of this application; Figure 7 is a step diagram illustrating the selection process of an image adjustment method according to other embodiments of this application. Figure 8A is a schematic image illustrating some embodiments of the present invention; Figure 8B is a schematic image illustrating some embodiments of the present invention; and Figure 9 is a schematic image illustrating some embodiments of the present invention. Domestic storage information (please note in order of storage institution, date, and number): None. International storage information (please note in order of storage country, institution, date, and number): None. 300: Method 310~370: Steps

Claims

1. An image adjustment method, comprising: capturing an image using an image capturing device; detecting a plurality of gestures in the image using a processor; identifying a gesture region formed by the gestures using the processor, thereby generating a first correction region in the image based on the gesture region; and adjusting the image using the processor based on the first correction region to generate the adjusted image.

2. The image adjustment method as described in claim 1, wherein the step of generating the first correction region in the image by the processor identifying the gesture region formed by the gestures comprises: identifying a perspective distortion contour of an object and the positions of a plurality of fingers of the gestures on the perspective distortion contour by the processor to form a plurality of first selection points; and identifying the gesture fixation time of the first selection points by the processor to form the first correction region.

3. The image adjustment method as described in claim 2, wherein the step of identifying the gesture area formed by the gestures by the processor and generating the first correction area in the image based on the gesture area further comprises: detecting whether the positions of the fingers move outside the first correction area based on the first selection points; and if the positions of the fingers do not move outside the first correction area, adjusting the image based on the first correction area by the processor.

4. The image adjustment method as described in claim 2, wherein the step of identifying the gesture area formed by the gestures by the processor, and generating the first correction area in the image based on the gesture area, further comprises: detecting whether the positions of the fingers move outward from one of the first correction areas based on the first selection points; if the positions of the fingers move outward from the first correction area, forming a second correction area in the image by the processor, so that the second correction area covers the object; and adjusting the image based on the second correction area by the processor.

5. The image adjustment method as described in claim 1 further comprises: detecting, by the processor, whether the adjusted image further includes a wrist; if the wrist is detected, forming a first selection area in the first correction area by the processor based on the positions of a plurality of fingers of the gestures and the position of the wrist; and performing image processing on the image by the processor based on the first selection area.

6. The image adjustment method as described in claim 5, wherein the step of detecting whether the wrist is further contained in the image by the processor includes: if the wrist is not detected, forming a boundary in the first correction area by the processor based on the position of two fingers of the finger positions; forming a second selection area by the processor based on the boundary and the first correction area; and performing image processing on the image by the processor based on the second selection area.

7. An image adjustment apparatus, comprising: a data splitter for receiving an image from an image capturing device, wherein the data splitter is configured to output a first image and a second image based on the image; a first processor coupled to the data splitter, wherein the first processor is configured to detect a plurality of gestures in the first image, wherein the first processor is configured to identify a gesture region formed by the gestures, thereby outputting a first signal and a second signal; and a second processor coupled to the data splitter and the first processor, wherein the second processor is configured to receive the second image, the first signal and the second signal, wherein the second processor is configured to form a correction region in the second image based on the first signal and the gesture region, wherein the second processor is configured to adjust the second image based on the second signal and the correction region, thereby outputting the adjusted second image to an image output device.

8. The image adjustment device as claimed in claim 7, wherein the image further includes an object with perspective distortion, wherein the first processor includes: a gesture recognition unit, wherein the gesture recognition unit is used to recognize the gestures and a perspective distortion outline of the object, so as to output the first signal to the second processor.

9. The image adjustment apparatus as claimed in claim 8, wherein the first processor further comprises: a gesture shaping unit, wherein the gesture shaping unit is configured to identify whether the gestures are held for a gesture shaping time based on the first signal, and output the second signal to the second processor.

10. The image adjustment apparatus as claimed in claim 7, wherein the second processor includes: an image correction unit, wherein the image correction unit is configured to adjust an object in the second image according to the second signal and the correction area.

Images