815 results about "Horizontal projection" patented technology

The invention provides an interactive display that is controlled by user gestures identified on a touch detecting display surface. In the preferred embodiment of the invention, imagery is projected onto a horizontal projection surface from a projector located above the projection surface. The locations where a user contacts the projection surface are detected using a set of infrared emitters and receivers arrayed around the perimeter of the projection surface. For each contact location, a computer software application stores a history of contact position information and, from the position history, determines a velocity for each contact location. Based upon the position history and the velocity information, gestures are identified. The identified gestures are associated with display commands that are executed to update the displayed imagery accordingly. Thus, the invention enables users to control the display through direct physical interaction with the imagery.

A method of automatically extracting data from an electronic document including tables is provided. The method includes: automatically identifying rows of the table using gaps in horizontal projections of the plurality of image sections, wherein at least some of the identified rows in close proximity are collected to form table formations; and automatically identifying columns of the table using at least some of the plurality of image sections that are vertically aligned, wherein the identified columns are grown in each of the table formations using gaps in vertical projections of the plurality of image sections until an obstruction is reached. The method further includes automatically identifying labels in the plurality of corresponding image sections to associate the identified labels with at least one of the identified columns and the identified rows; and automatically extracting data from cells of the table formed by the identified rows and columns.

A golf putter head with a front edge is used for striking a golf ball in an essentially linear contact area horizontal to the ground when putting and an opposed back edge. A length is defined between a toe edge which extends from the front edge to the back edge of the blade and an opposed heel edge, and a thickness is defined between a top side bordered by the edges and an opposed bottom side. The golf putter includes a non-horizontal groove on the front edge at least adjacent to a ball contact portion of the head defined by a non-horizontal projection corresponding to the non-horizontal groove.

The invention provides an interactive display that is controlled by user gestures identified on a touch detecting display surface. In the preferred embodiment of the invention, imagery is projected onto a horizontal projection surface from a projector located above the projection surface. The locations where a user contacts the projection surface are detected using a set of infrared emitters and receivers arrayed around the perimeter of the projection surface. For each contact location, a computer software application stores a history of contact position information and, from the position history, determines a velocity for each contact location. Based upon the position history and the velocity information, gestures are identified. The identified gestures are associated with display commands that are executed to update the displayed imagery accordingly. Thus, the invention enables users to control the display through direct physical interaction with the imagery.

In some embodiments, the invention includes a method for locating text in digital images. The method includes scaling a digital image into images of multiple resolutions and classifying whether pixels in the multiple resolutions are part of a text region. The method also includes integrating scales to create a scale integration saliency map and using the saliency map to create initial text bounding boxes through expanding the boxes from rectangles of pixels including at least one pixel to include groups of at least one pixel adjacent to the rectangles, wherein the groups have a particular relationship to a first threshold. The initial text bounding boxes are consolidated. In other embodiments, a method includes classifying whether pixels are part of a text region, creating initial text bounding boxes, and consolidating the initial text bounding boxes, wherein the consolidating includes creating horizontal projection profiles having adaptive thresholds and vertical projection profiles having adaptive thresholds.

The invention provides an electric pressure cooker, comprising a cooker body (100) and a cooker cover (200); a cap (300) raised towards the outer part of the cooker body along a radial direction is arranged on the cooker body; a back cover plate (400) suitable for forming a holding cavity with the cap is further arranged on the cooker body; a push rod component is held in the holding cavity, and a penetrating hole (301) allowing the top part of the push rod component to extend out of the outer part of the cap is arranged on the cap; the holding cavity further holds a switch (2) driven by the push rod component, and a horizontal projection of the penetrating hole (301) is spaced from the horizontal projection of the switch (2). The electric pressure cooker provided by the invention can guarantee that the switch position and the penetrating hole position are free from overlapping part on vertical direction; when waterlog is formed on the top face of the cap, even though water which is not timely discharged is flowed from the penetrating hole to the holding cavity, water cannot directly fall on the switch; therefore, the electric pressure cooker can effectively prevent switch or microswitch particularly from water immersion; the switch or microswitch is stable in use.

The invention discloses a method for automatically extracting road information in a vehicle-mounted laser scanning point cloud. The method for automatically extracting the road information in the vehicle-mounted laser scanning point cloud comprises the steps that all scanning lines are extracted from the discrete point cloud according to the information, such as the traveling track, the laser point scanning angle and the scanning time, which is recorded by a vehicle-mounted system, and a half scanning line index suitable for data processing is established; the spatial relation between two adjacent points is analyzed, laser point generation clustering is conducted, and dynamic window point sets which can describe the type characteristics of certain types of ground objects are generated; the main geometrical characteristic factors, comprising elevation difference factors and horizontal projection distance factors, of the different ground object window point sets are analyzed; window starting point types are judged according to the main geometrical characteristic factors of the window point sets, movement type dynamic window classification is conducted from a central angle point to the two sides according to the half scanning line index until a non-road-surface point is found; clustering and denoising are conducted on roadside points according to the distribution relation of bottom points of roadside stones and by the adoption of the principle of consistency between the scanning angle and the distance.

The invention relates to fields of a vehicle plate character segmenting method based on horizontal projection and connected domain analysis and pattern recognition. The method comprises the following steps of: 1) locating a vehicle plate subimage; 2) computing the optimal threshold value of the subimage; 3) binarizing the image to obtain a binarized image; 4) rotating the binarized image at an optimal angle; 5) performing slant correction on the rotated image; 6) performing horizontal projection on the binarized image; 7) performing connected domain analysis on the binarized image to obtain a character block; 8) verifying the character block by using priori knowledge and removing a false character block; 9) performing character segmentation by combining the horizontal projection in the step 6) and the connected domain result in the step 7) so as to obtain the horizontal position of each character; 10) computing an upper border and a lower border of the vehicle plate character according to the binarized image in the step 5); 11) computing each border of a character rectangle according to the upper border and the lower border and the central position of the character; and 12) performing fine adjustment according to a horizontal projection curve to obtain a character-segmenting result. By the method, the segmentation of the vehicle plate character is reliable and stable, the resistance to image noise and interference is high, and the segmenting efficiency is high.

The invention discloses an optic disc projection location method synthesizing vascular distribution with video disc appearance characteristics, which comprises the following steps of: (1) extracting an interest retina fundus image region by use of a mask operation; (2) carrying out normalization enhancement on a fundus image based on an image observation model; (3) achieving extraction and segmentation of the fundus image by using a non-vascular structure inhibition operator and combining with a hysteresis multi-threshold processing technology; (4) setting a vertical window of double main blood vessel width to slide on a blood vessel segmentation image along the horizontal direction and calculating a vascular distribution degree D(x) at each horizontal position x to obtain a distribution degree curve of a horizontal projection, wherein the minimum value point of the curve is determined to be optic disc horizontal coordinate xod; (5) setting a rectangular window side length of which is equal to the optic disc diameter to slide up and down at the horizontal coordinate xod, estimating local region brightness IN(xod, y) and edge gradient information gN(xod, y) respectively, drawing a vertical projection curve reflecting a change of a characteristic value f(y)=IN(xod, y)*gN(xod, y), wherein a maximum value point of the curve is optic disc vertical coordinate yod. The method has a simple algorithm, a high success rate and excellent robustness.

The invention discloses a face recognition-based fatigue driving detection method. The method includes the following steps that: human face video image acquisition is carried out; an integral projection algorithm is adopted to carry out eye and mouth positioning on the first frame of image, the images of a left eye portion, a right eye portion and a mouth portion are extracted; an adaptive particle filtering-based eye tracking algorithm is adopted to carry out eye tracking; an improved horizontal projection-based eye and mouth state recognition method is adopted to carry out recognition; eye and mouth fatigue information extraction is carried out, a PERCLOS value, blink frequency, eye closing time and the number of times of yawning are calculated; and fatigue judgment is performed on a driver based on the PERCLOS value, the blink frequency, the eye closing time and the number of times of yawning. According to the defects of an original horizontal projection method, an improved horizontal projection method is adopted to recognize eye and mouth states, and therefore, high recognition accuracy and high adaptability can be achieved; and the fatigue judgment algorithm can improve judgment accuracy.

An integrated hands-free, point of view, action-sports, digital video camera (or camcorder) (10) includes: a rotary horizon adjustment controller (14) for adjusting the orientation of a horizontal image plane (16) recorded by an image sensor with respect to the orientation of a camera housing (22); a laser alignment system with laser sources (48) capable of projecting light to define a horizontal projection axis (52) that is coordinated with orientation of the horizontal image plane (16); a manually operable switch (80), which covers a microphone (90) whenever the switch (80) is in the OFF position, for controlling video data capture; and a “quick-release” mounting system (120) that retains a desired orientation of the camera (10).

The invention provides a method and a device for identifying second-generation identity cards based on intelligent mobile equipment. The method comprises the following steps: acquiring an image of a second-generation identity card by a camera; performing gray calculation and binarization processing on the image of the second-generation identity card to acquire binary image data; horizontally projecting the binary image data to acquire each black block; acquiring the region of citizen identification number information according to the black blocks; acquiring the name information region and the address information region according to a preset second-generation identity card template. According to the method, when the second-generation identity card image is processed, gray calculation, binarization processing, horizontal projection, vertical projection, relative coordinate position and other basic algorithms are used, and the algorithms can run conveniently in the intelligent mobile equipment; a second-generation identity card image shot by the method only needs to comprise content to be identified, the method is low in image shooting requirement, can be applied to the intelligent mobile equipment, and can be used by users conveniently.

The invention relates to an ID No. localizing and recognizing method, which belongs to the OCR technical field of locating and recognizing an ID No. from images containing the ID No. In the method, the horizontal projection value of an image is utilized to divide the image into one or more line areas; then, the characteristics of the aspect ratio of both the image and the ID No. in the line areas are utilized to remove lines where the ID No. is impossibly located; subsequently, each line area where the ID No. is possibly located is divided into one or more row areas, and the characteristics of small number and small space between digits of the ID No. are utilized to determine the position of the ID No. on the image; finally, the ID No. within the image is recognized with an recognition engine. The ID No. localizing and recognizing method can complete the acquisition of the information about ID, Military ID, Passport, Driver's License numbers and so on simply, conveniently and rapidly to greatly reduce the labor cost and increase the working efficiency.

The invention provides a defect detecting method and a defect detecting device. The method comprises the steps of acquiring an image of a region of interest (ROI); setting two threshold values, performing binarization processing on the ROI image according to normal pixel points of the ROI image with the pixel value within the two threshold values and defect pixel points of the ROI image with the pixel value beyond the two threshold values, so as to obtain a binarization image; performing vertical projection and / or horizontal projection on the defect pixel points of the acquired binarization image so as to obtain projection images of the defect points; and detecting the defects from the projection images. The method can realize detection of low contrast defects.

The invention provides a video image character detecting method based on sparse expression, which comprises the following steps of: S1, resampling a video sequence to obtain a color video image, and converting the gray level and the multi-scale of the color video image to obtain a multi-scale gray level image; S2, performing edge detection and morphological closed operation to the multi-scale gray level image with an improved Sobel operator to obtain an edge image and filter the edge density of the edge image; obtaining a candidate character region through connected domain analysis and regular analysis; and S3, performing vertical projection and horizontal projection to the candidate character region, diving a vertical projecting image and a horizontal projecting image to obtain candidate character lines, dividing the candidate character lines into small regions through sliding windows, extracting the edge characteristics of the small regions, respectively classifying each small region with a classifying method based on the sparse expression, judging whether the small regions are character regions, judging the candidate character lines according to the judging result of the small regions to obtain and output a final character line region.

The invention discloses a millimeter-wave 360-DEG omnidirectional-scan dielectric cylinder lens antenna comprising three dielectric cylinder lenses, three feed source antenna arrays with scan ranges of 120 DEG and four round metal discs. One of the three dielectric cylinder lenses is respectively coaxially arranged among the four round metal discs, one of the three feed source antenna arrays is respectively arranged between the edges of two adjacent round metal discs, the difference between two of the three feed source antenna arrays on a horizontal projection surface is 120 DEG, and a phase central plane of each feed source antenna array is superposed with a focal plane of each dielectric cylinder lens. The invention realizes 360-DEG omnidirectional scan in the horizontal direction; the three dielectric cylinder lens antennas are partitioned by parallel round metal disc-shaped plates, and the scan of each homogeneous dielectric cylinder lens is not interfered by the other two lenses,thus the scanning beam of each layer of cylinder lens antenna is totally consistent; and the millimeter-wave 360-DEG omnidirectional-scan dielectric cylinder lens antenna can be conveniently connected with a printed integrated circuit. The millimeter-wave 360-DEG omnidirectional-scan dielectric cylinder lens antenna is applied to the fields of space flight communication, satellite communication, electronic countermeasure and the like.

Food containers formed of sheet plastic are latchably stackable on one another. Each container has base (14) and lid (16) elements, with one of them having an outer rim part with a pair of long handle sections (80, 82) that can be pivoted up to form a handle assembly for carrying the container. The sections that form handles are formed in the lid element (16) rather than in the base element (14), so a person does not have to contend with long bouncing sections if the person eats a meal out of the base. One of the elements has vertically undercut grooves (50) and the other element has horizontal projections (52) that slide into and along the grooves. The grooved element has vertical passages (120) along which the projections can move vertically until they can slide into and along the grooves.

The invention provides a method for analyzing and recognizing the structure of a handwritten mathematical formula in a natural scene image. The method comprises the steps of S1, converting the gray matrix of a natural scene image into a local contrast matrix, and conducting the binary classification on the local contrast matrix based on the otsu method to obtain a binary matrix; S2, analyzing the connected domains of the binary matrix obtained in the step S1, and removing non-character type connected domains to obtain character type connected domains; S3, detecting formula structural elements and other special structural elements in the character type connected domains based on the correlation coefficient method, and separately marking out all detected special structural elements; S4, dividing the binary matrix obtained in the step S1 based on the horizontal projection method; S5, recognizing each character type connected domain via a convolutional neural network; S6, defining an output sequence and outputting recognized results according to the corresponding sequence in the latex layout format. According to the technical scheme of the invention, by means of the method, the expression problem of elementary mathematical formulas during the OCR recognition process can be effectively solved.

The invention discloses an efficient DSP banknote serial number recognizing method, which relates to the technical field of image recognition technologies. The method of the invention mainly comprises the key steps of banknote edge extraction, facing direction recognition, serial number location, character segmentation and character recognition. Through banknote edge extraction, the banknote edge in an image is searched and fitted. Facing direction recognition is carried out to determine the front and the back of a banknote and judge whether the banknote is inverted so as to know the rough position of the serial number. Serial number location refers to locating the serial number coarsely based on prior knowledge, carrying out tilt correction on the basis and locating the serial number precisely using horizontal projection. Then, the characters of the precisely located serial number are segmented to obtain independent characters, and on the basis, the gray scale and size of the obtained segmented characters are normalized. Finally, the full-pixel characteristics of the character image are extracted, and the characters are identified using a neural network method.

The invention provides an impact danger evaluation method of a mine pre-exploiting coal seam. The method comprises the following steps: establishing a mine area three-dimensional digital geological model and visualizing the model; grasping a space occurrence environment of a coal seam; determining a geological master control factor of a rock burst; performing grid division on a horizontal projection of a pre-exploiting coal seam area, quantifying a geological master control factor of each grid point, and forming a coal seam impact danger evaluation index system; generating an isoline nephogram of each index; establishing a mine pre-exploiting coal seam impact danger evaluation model; and evaluating an impact danger grade of each grid point, obtaining an impact danger grade of any position of the mine pre-exploiting coal seam area, and generating and visualizing an impact danger grade nephogram of the mine pre-exploiting coal seam area. According to the invention, by use of a digital visualization geological information technology, an impact danger area is preliminarily grasped in advance before the coal seam is exploited, relevant prevention and control measures can be taken in a danger area, and method provided by the invention has wide application prospect for safe coal seam exploitation of a rock burst mine.

The invention provides a method for evaluating a three-dimensional roughness degree of a rock mass structure face. The method comprises the steps that a three-dimensional geometric model of the rock mass structure face is established, and the rock mass structure face is dispersed into a series of triangular micro elements based on a Delaunay triangulation algorithm; according to a shearing direction, possible parts at which contact may take place when shearing effects take place to the rock mass structure face are determined, namely potential contact micro elements are determined; a total projection area formed by all the potential contact micro elements of the rock mass structure face on the face perpendicular to the shearing direction is computed; and a ratio of the total projection area to a horizontal projection area of the rock mass structure face is computed, and the ratio is used to describe the three-dimensional roughness degree of the rock body structure face. According to the invention, in combination with a shear damage mechanism of the structure face, a roughness degree evaluation index with an explicit theoretical basis is acquired; and the index not only can reflect geometric morphology of the structure face in the shearing direction and consider anisotropy of the rock mass roughness degree, but can also has certain correlation with shear strength of the structure face, so that a shear strength estimation model can be served better.

The invention discloses a license plate positioning identification method based on a support vector machine and a convolutional neural network. The method comprises the following steps of using the weighted grayscale algorithm to carry out graying processing and histogram equalization on an original color license plate image so as to acquire an equalized grayscale image; carrying out edge detection on the equalized grayscale image and acquiring an edge image; carrying out binarization on the edge image; using a morphology to operate the license plate image so as to process and acquiring a license plate candidate area image; using a SVM discrimination model to classify and acquiring a license-plate accurate positioning image; using a vertical and horizontal projection combination method tocarry out image segmentation and acquiring a single character image; using a normalized function to carry out normalization processing on each license plate character; and using a convolutional neuralnetwork model license plate character identification model to identify and outputting and displaying an identification result. In the invention, the robustness of a license plate character identification algorithm is effectively increased, and the method has a high identification rate and is suitable for the license plate positioning and identification under a complex background.

The invention discloses an indicating value identification method of a dial instrument. The indicating value identification method of the dial instrument belongs to the field of artificial intelligence. The technical scheme of the indicating value identification method of the dial instrument is that a computer automatically acquires a dial plate image of the dial instrument, divides out needed image feature regions, obtains the feature of a number to determine the numerical value of the number according to centre-of-gravity position, perpendicular line features and horizontal projection operations, and finally computes the actual evaluation of the dial instrument through an abscissa of the number and a former pointer and a scale mark. The image processing method for reading the indicating value of the dial instrument can accurately acquires the coordinate value of the pointer and coordinate value of an intersection of the pointer and scale marks, can avoid indicating value calculation deviation problems caused by camera lens distortion, uneven scales of dial plates, or the noncoincidence of a fixed point of the pointer and the centre of a circle which passes through the scale mark of the dial plate due to the fact that the angle method is utilized in the prior art, improves the efficiency and accuracy of reading the indicating value of the dial instrument, is applicable to a plurality of hardware platforms, and has high transportability and stability.

The invention discloses a paper currency face value identification method and device based on a magnetic image. The paper currency face value identification method comprises the following steps: laterally magnifying the magnetic image by multiple times, carrying out contrast stretching, high-low threshold binaryzation, safety line and magnetic code image positioning section by section and safety line and magnetic code cutting, drawing a safety line and magnetic code horizontal projection curve, identifying the face value of paper currency according to the safety line and magnetic code curve rule, identifying four directions of the paper currency according to the position of a magnetic signal of a crown character code, identifying the version of the paper currency according to whether magnetic ink exists, verifying the face value direction, and the like. According to the paper currency face value identification method and device, a safety line and magnetic code image is cut by adopting a sectional positioning method and is further verified by using the face value of the paper currency, which is identified by utilizing the safety line and magnetic code projection curve rule, and the face value direction identified by other identification measures, so that the face value direction error probability of the paper currency is greatly reduced, relatively high face value direction rate is achieved and the paper currency processing level of financial self-service equipment is improved.

Apparatus, systems, and methods disclosed herein operate to produce an image alignment shift vector used to shift left and right image portions of a stereoscopic image with respect to each other in order to reduce or eliminate undesirable horizontal and vertical disparity components. Vertical and horizontal projections of luminance value aggregations from selected left and right image pixel blocks are correlated to derive vertical and horizontal components of a disparity vector corresponding to each left / right pixel block pair. Disparity vectors corresponding to multiple image blocks are algebraically combined to yield the image alignment shift vector. The left and / or right images are then shifted in proportion to the magnitude of the image alignment shift vector at an angle corresponding to that of the image alignment shift vector.

The utility model relates to a detection method of eye state based on cascade sort and Hough circle transform, belonging to the field of pattern recognition, which is characterized in the following steps: to acquire a face image; to carry out skin color segmentation in the YCbCr color space to acquire the position information of the skin color area using an ellipse skin model; to detect the rectangular eye area with the method of eye detecting window traversal with a cascade eye classifier; to merge a rectangle by rectangular merge method to get a merged eye rectangular linked list; to operate edge detection and binarization in turn on every rectangular eye area in the merged eye rectangular linked list with a Sobel operator to get an binary image; to detect the eye state of every binary image in turn with horizontal projection method; to further detect the eye state by Hough circle transform detection method if whether the present state is eye closure is not certain. The utility model increases the speed of eye detection, tracks and analyzes the eye state with the skin color segmentation, which is suitable for attention detection and fatigue detection.

The invention provides a method for carrying out Bayes judgment on modeling for a video image based on color-texture dual characteristic vectors so as to realize moving target detection. The method comprises the following steps: 1. obtaining a video frame; 2. preprocessing an image; 3. background modeling and carrying out motion detection by utilizing Bayes judgment, wherein the background modeling comprises image color-texture dual characteristic vectors, respectively adopting different characteristic vectors according to the variation of interframe difference of a pixel point, expanding the original Bayes judgment to be two-dimensional due to the independence of the characteristic vectors, setting model parameters and updating control parameters so as to adapt to the change of the state of a moving object; 4. shadow detection, using a texture model to detect a shadow candidate point and eliminating the shadow; 5. processing after the detection, using horizontal projection and vertical projection to determine a foreground area and perfecting the detection result in a divided area through block analysis; and 6. updating a background image, respectively updating according to a detection classification result and setting self-adaptive updating rate parameters so as to adapt to illumination change.

The invention discloses a paper currency authentic identification method and device based on magnetic images. Magnetic images of paper currency obtained by a magnetic image sensor are processed, after image enhancement processing, tilt correction pre-processing and the like are carried out on the magnetic images, a magnetic image histogram is calculated, binarization processing is carried out, two binaryzation magnetic images of safety lines are cut out, horizontal projection is carried out on the two cut binaryzation magnetic images, whether the features of impulse waveforms of the horizontal projection curve of the two binaryzation magnetic images of the safety lines conform to set regulations is judged, and the paper currency is judged to be real currency if all the features conform to the set regulations. According to the method and device, due to the fact that a high threshold value and a low threshold value are adopted for carrying out binaryzation on the magnetic images, the binaryzation magnetic images of safety lines are cut out, the features of the two binaryzation magnetic images of safety lines are recognized, and the paper currency is judged to be the real currency if all the features conform to the set regulations.

The invention discloses a method and a device for utilizing a digital camera to obtain rice canopy leaf area index. The method includes the following steps: (1) the digital camera is arranged above the outer portion of a rice canopy, a lens faces downward, a lens primary optical axis is perpendicular to a rice canopy horizontal projection plane, and a rice canopy original color image is shot; (2) the rice canopy original color image is converted into a gray level image; (3) the gray level image is converted into a binary image only containing a black image element and a white image element; (4) rice canopy porosity is extracted from the binary image; and (5) the leaf area index is calculated according to the extracted rice canopy porosity. According to the device and the method, only a common digital camera is needed to shoot a rice canopy image above the outer portion of the rice canopy in vertical overlook mode, manual measurement through destructive picking of rice leaves in the field is not needed, the rice canopy leaf area index (LAI) can be obtained rapidly in real time, and basic parameters are provided for rice remote yield estimation and rice growing condition monitoring.