2467 results about "Image pre processing" patented technology

Face detection techniques are provided that use a multiple-stage face detection algorithm. An exemplary three-stage algorithm includes a first stage that applies linear-filtering to enhance detection performance by removing many non-face-like portions within an image, a second stage that uses a boosting chain that is adopted to combine boosting classifiers within a hierarchy “chain” structure, and a third stage that performs post-filtering using image pre-processing, SVM-filtering and color-filtering to refine the final face detection prediction. In certain further implementations, the face detection techniques include a two-level hierarchy in-plane pose estimator to provide a rapid multi-view face detector that further improves the accuracy and robustness of face detection.

The invention discloses a view line tracking method and an assistant system for the handicapped by using the method. The method comprises the steps of image pretreatment, the orientation of a human eye area by utilizing Harr features, blinking recognition, the inspection and judgment of LED reflecting lightspot in pupils, the accurate position of pupil centre, the calculation of view line direction and so on. The system comprises an embedded-like platform, a camera, a display screen and four LED and wheelchair running control modules which are installed at the four corners of the display screen and arranged into a rectangular. The system is an embedded-type system, which carries out blinking inspection, the inspection of the reflecting lightspots against infrared light sources on corneas, the accurate position of the pupil centers and the judgment of view line directions by the camera and a processor, tracks the view line of human eyes and, meanwhile, carries out the recognition of the status of the human eyes by judging the view line directions of the human eyes when gazing on the screen, thus realizing the functions of wheelchair control, music play control, text reading and webpage rolling. The invention is convenient for use and has high accuracy, thereby being capable of bringing great convenience for the lives of the handicapped.

The invention belongs to the field of intelligent automobile road detection and relates to a method for detecting road information and identifying forward vehicles based on vision. The method comprises image preprocessing, lane line characteristic parameter extraction, region-of-interest segmentation and vehicle outline identification. According to the method for detecting the road information and identifying the forward vehicles based on vision, the complexity of computation is simplified by extracting the regions of interest, filtering out background regions and reducing the processing scope; the processing result of each frame of image is obtained through fixed computation times by use of a line-by-line retrieval method, and differing from the characteristic, namely linear fitting on each bright spot, of Hough conversion, the method has outstanding advantages in algorithm instantaneity; the instantaneity of the Robinson direction model operator is improved, and an intermediate variable is set to reduce the computation times of each pixel point. The regions of interest are screened and judged by use of an information entropy and a vehicle tail symmetry characteristic in the target region, and therefore, the omission factor and the false drop rate of the algorithm are reduced.

A CCD captures a subject image having passed through a taking lens and an image processing circuit performs various types of image pre-treatment including gamma correction and white balance on image data corresponding to n lines×m rows output by the CCD. The image processing circuit also performs format processing on the data. The data are then compressed at a compression circuit. The white balance adjustment and the like are implemented in line sequence at a line processing circuit which engages in signal processing in pixel sequence in units of individual lines in the output from the CCD. The image data having undergone the pre-treatment are then subjected to format processing prior to JPEG compression, at a block processing circuit that engages in signal processing in units of individual blocks each ranging over an n×m (N>n, M>m) block. In other words, the signal processing is performed in block sequence.

A method and apparatus are disclosed for an image preprocessing device that automatically detects chestwall laterality; removes border artifacts; and segments breast tissue and pectoral muscle from digital mammograms. The algorithms in the preprocessing device utilize the computer cache, a vertical Sobel filter and a probabilistic Hough transform to detect curved edges. The preprocessing result, along with a pseudo-modality normalized image, can be used as input to a CAD (computer-aided detection) server or to a mammography image review workstation. In the case of workstation input, the preprocessing results improve the protocol for chestwall-to-chestwall image hanging, and support optimal image contrast display of each segmented region.

The invention discloses an automatic character extraction and recognition system and method for a low-resolution medical bill image. The system comprises an image preprocessing module, a field segmenting module, a single character segmenting module and a character recognizing module. The method comprises the steps of image preprocessing, field area recognizing, character string segmenting and character recognizing and verifying. The automatic character extraction and recognition system and method can be better suitable for automatic character extraction and recognition of the low-resolution medical bill image. The information can be fully utilized by performing layout analysis on a bill. For the image of which the image quality is low and the noise and the image resolution influence are very high, a character string is conveniently segmented into single characters through the semanteme of each field area, and then recognition on the image is converted into recognition on the single characters; for example, an invoice number composed of pure numbers can be recognized through a method special for processing an image only containing numbers, and when the invoice number is recognized, the recognizing range is limited within ten numbers from 0 to 9, and therefore the recognition rate can be greatly increased.

An image processing apparatus includes an image input device that reads an original image and obtains image data from the original image by selecting one of plural types of image reading modes of the image input device, an image pre-processing mechanism that performs at least one pre-processing relative to the image data obtained by the image input device, an image pre-processing selecting mechanism that selects at least one pre-processing according to the image reading mode selected by the image input device and causes the image pre-processing mechanism to perform the selected at least one pre-processing, and an information extracting mechanism that extracts specific information included in the image data subjected to the at least one pre-processing performed by the image pre-processing mechanism.

An apparatus and method for generating and consuming a three-dimensional (3D) data format to generate a realistic panoramic image are provided. The apparatus may include an image preprocessing unit to search for a matching point between images captured by a plurality of cameras, and to extract, as image information, at least one of a depth value, a texture value and object division information from each of the captured images, an image information structuring unit to structure 3D data to use the extracted image information to generate a realistic image, a 3D data format storage unit to store format information of the to structured 3D data in a database (DB), realistic image generating unit to generate a realistic panoramic image using the stored format information of the 3D data, and a realistic image rendering unit to perform rendering on the generated realistic panoramic image.

The invention relates to a front small-region object recognition and vehicle early warning method, and belongs to technical field of early warning for collision in front of vehicles. The front small-region object recognition and vehicle early warning method specifically comprises the steps that an image of a target to be recognized in front of a vehicle is acquired, and a region of interest (ROI)image is obtained; image preprocessing is performed on the obtained region of interest image, the preprocessed region of interest image is inputted into an improved YOLO convolutional network structure model to perform target recognition, and a target regression frame and a target category are outputted; the recognition result is inputted into a vehicle early warning system, if the target regression frame is located beyond the range of a vehicle driving route or the target is recognized to be of a non-dangerous category, the target is marked as a non-dangerous target, and the vehicle does notperform early warning; and if the target regression frame is located within the vehicle driving route and the recognized object belongs to a dangerous category or the object cannot be recognized but has certain speed features, the target is marked as a dangerous target, the vehicle performs early warning to remind a driver to pay attention so as to avoid occurrence of an accident.

The invention discloses an intelligent system for monitoring vehicles and people in a community. The intelligent system comprises a monitor image collection module, a monitor image pre-processing module, a vehicle contour and license plate image information recognition module, a vehicle information database, a face image information recognition module, a people information database, an image information identification verification and positioning speed-measurement module and an intelligent management module. The monitor image collection module collects image information of the vehicles and the people, the monitor image pre-processing module pre-processes the image information, the vehicle contour and license plate image information recognition module processes, extracts and recognizes vehicle image information, and the face image information recognition module extracts and recognizes obtained people face information; and the image information identification verification and positioning speed-measurement module performs identification verification an positioning testing, and an intelligent control module is used for human-machine interactive interface operation and intelligent processing. The intelligent system monitors the vehicles and the people in the community and performs entrance guard management, thereby guaranteeing the trip safety of the people in the community.

The invention relates to a detection method for vehicle license plate real-time positioning character segmentation in the technical field of video monitoring, which comprises the following steps of: obtaining a video frame from image acquisition equipment; carrying out image preprocessing; increasing a signal-to-noise ratio; carrying out grey scale transformation; computing a threshold value by adopting an Otsu binarization method and converting a vehicle image into a binary image; firstly carrying out closed operation by using a structural element with the size of length pixels, separating a communicated region at a fine position and smoothing burrs appearing on the edge of the region; carrying out contour detection; and carrying out license plate region accurate positioning: accurately segmenting out each character. The invention has lower requirements for image color, a large amount of system memory resources of a computer can not occupied, the operational speed is quickened after an input image is converted into a grey-scale image, the accurate position of each character can be rapidly found, and each character is segmented out by applying an image shearing method.

The invention provides an automatic recognition and an extraction method and a device for a bill information area and relates to the fields of computer image processing and information recognition. According to the automatic recognition and the extraction method for the information area of the bill, processes of the information recognition, edge and shading processing, character zone enhancement processing, information area extraction and the like are performed through bill image preprocessing and according to an information area character database which is built in advance through self-learning and training of the information area. The automatic recognition and the extraction method for the bill information area has the advantage of being capable of automatically recognizing and extracting interested area information of multiple bills with good accuracy and adaptability to save manpower and time of the bill processing.

The invention discloses an image processing method for automatic pointer-type instrument reading recognition. The method comprises the following steps: (1) Hough circle detection is carried out on the image, a weighted average method is used for positioning the circle center and the radius of a dial, and a dial region square image is extracted; (2) the image is pre-treated, and a binary thinning image of the instrument pointer is extracted; (3) a central projection method is used for determining a pointer angle; (4) a zero graduation line and full graduation line position templates are extracted, and a range starting point and ending point positions are calibrated; (5) by using template matching, zero graduation line and full graduation line angles are obtained; and (6) according to the pointer angle, the zero graduation line angle and the full graduation line angle, the pointer reading is obtained through calculation. Thus, the problem that the instrument dial position on the acquired image is not fixed as the relative position between a camera and the pointer-type instrument is not fixed can be solved, subjective errors as the reading of the instrument is read manually can be eliminated, the efficiency and the precision can be improved, safety of people is ensured, the application range is wide, and robustness is strong.

The present invention provides a deep convolution neural network-based traffic flow density estimation method. The method comprises the steps of collecting road video images by a camera, sending multi-scale pyramid image blocks into a convolution neural network through image pre-processing, extracting simple features and abstract features from a bottom layer to a high layer, and obtaining a distribution density image of each scale of traffic flow image; learning a mapping from the multi-scale distribution density image to a distribution density image of an overall image and a number of all vehicles in the image by using a fully connected network layer; dividing regions of interest of a distribution density image of a video image output by the convolution neural network, summing pixels of the regions of interest so as to obtain a number of vehicles of a single lane or multiple lanes; and calculating according to a region length so as to obtain an instantaneous traffic flow density of the region. Through adoption of the method, vehicles are calculated and traffic flow density is estimated in real time more accurately.

The invention discloses a moving target analyzing and tracking method and system based on video monitoring. The moving target analyzing and tracking method comprises the following steps of: monitoring video acquisition, acquiring video streaming recorded by a monitoring camera; performing image preprocessing: primarily processing an image of the video streaming, and acquiring a processed image; performing target recognition: performing target recognition classification on each foreground object of the processed image, wherein the classified type of targets comprises persons, vehicles and objects; performing motion track analysis: analyzing the motion track of each target according to the setting of an alarm rule, marking a target of which the motion track is matched with the alarm rule as a suspected target, and giving out an alarm; and tracking the target: tracking the suspected target, and recording the actual motion track and the actual motion direction of the suspected target. According to the method, the alarm is automatically given aiming at an abnormal event, the possibility of missing report and error report is reduced, and the workload of security monitoring personnel is lightened.

The invention discloses an intelligent video analyzing system and method for automatically identifying a fake plate vehicle. The system comprises a video collecting unit, an image preprocessing unit, an intelligent video analyzing unit and a database, wherein after vehicle video information collected by the video collecting unit is processed by the image preprocessing unit, and is then transmitted to the intelligent video analyzing unit, the vehicle information and the database information are compared by the intelligent video analyzing unit, and the vehicle information is analyzed, matched and judged by software so as to automatically identify a suspected vehicle and carry out system prompt or alarm. By adopting the technical scheme disclosed by the invention, the participation of personnel is greatly reduced, the identification accuracy and efficiency are increased, and the intelligent video analyzing system and method disclosed by the invention can be used for assisting the public security bureau and the criminal investigation department to carry out real-time monitoring on the fake plate, false plate and counterfeit plate vehicles in the illegal criminal cases.

The invention relates to an adaptive low-illumination visible image and infrared image fusion method, and belongs to the field of digital image processing. The method comprises the steps: image preprocessing, NSCT transformation, frequency domain coefficient fusion and an NSCT inversion. The method mainly achieves the multi-scale decomposition of a bright image and an infrared visible image, extracts high-frequency components and low-frequency components, and selects different fusion rules to carry out the frequency domain fusion according to the characteristics of the high-frequency components and low-frequency components. The NSCT inversion part is mainly used for carrying out the multi-scale inversion of the obtained fusion high-frequency and low-frequency components, obtaining the gray scale image after fusion, then carrying out the weighting of the gray scale image after fusion and an original color visible image, and obtaining a color fusion image. The method can effectively keep more detail information of the original image, can improve the contrast and resolution of the fusion image, and can be widely used in the fields of intelligent traffic, video monitoring, medical diagnosis, target detection and national defense security.

The present invention provides a reconstruction method of human posture based on the geometrical skeleton, including:determining human skeleton pattern; obtaining 3D human skeleton pattern, pre-processing image; obtaining bianry image of separation of the background and the human; acquiring human geometrical skeleton; obtaining linear geometrical skeleton; labelling articulare of the start frame; bonding the manual labelling articulare on the geometrical skeleton, shortening the initial error; tracing the articulare by light stream method; obtaining the new position by the light stream method; processing error judgement and position correction to the new articulare obtained by the trace with the combined geometrical skeleton; processing line correction calculated by the light stream method; re-constructing the human posture; converting the two-dimensinal coordinate of the articulare to the 3D skeleton pattern by the parameter evaluating method of the proportion orthogonal projection model. The invention improves accuracy of the posture reconstruction, obtaining a high processing efficiency, capable of processing stable and effect human posture reconstruction in the intelligent video monitor system.

A gate inhibition and work attendance device based on face discrimination technique are disclosed those include: cam used to read the face images, embedded system used to transmit the video information, input device used to input the identification information and computer used to distinguish the images and manage the work attendance. Said cam is connected with the embedded system, said embedded system is connected with the input device, and said embedded system is connected with the computer data. The gate inhibition and work attendance device also include mirror face used to confirm the side position of face, the cam is mounted on the top of mirror face, the optimal visual range of the cam is matched with the mirror face; said computer includes: image acquisition module, face image library, face detecting position module, image preprocessing module, face exercising module and face discrimination module. The invention provides the gate inhibition and work attendance device based on face discrimination technique with characterized that high discrimination success rate, easy to realize, high-speed to discriminate and judge, convenient to install and low implement cost.

The invention provides a face detecting and tracking method and a device. The method comprises the steps of inputting a face image or a face video, preprocessing the face image or the face video in an illumination mode, detecting a face by usage of an Ada Boost algorithm, confirming an initial position of the face, and tracking the face by the usage of a Mean Shift algorithm. According to the face detecting and tracking method and the device, a self-adaptation local contrast enhancement method is provided to enhance image detail information in the period of image preprocessing, in order to increase robustness under different illumination conditions, face front samples under different illumination are added to training samples and accuracy of the face detection is increased by adoption of the Ada Boost algorithm in the period of face detection, in order to overcome the defect that using color of the Mean Shift algorithm is single, grads features and local binary pattern length between perpendiculars (LBP) vein features are integrated by adoption of the Mean Shift tracking algorithm in the period of face tracking, wherein the LBP vein features further considers using LBP local variance for expressing change of image contrast information, and accuracy of the face detection and the face tracking is improved.

The invention discloses a system for analyzing plant leaf features based on image scanning. The system comprises the following steps of: (1), preprocessing an image; (2), analyzing and calculating the features of a leaf image; (3), matching with a leaf template; (4), clustering by color; and (5), analyzing specks. The system disclosed by the invention has the advantages that the automation level is high, manual operation in an analytic process is reduced, the automation degree is improved, and meanwhile, manual operation errors are avoided; the execution efficiency is relatively higher than that of a traditional canny operator and a traditional compass operator; the accuracy is higher; and mending operation can be automatically carried out on an incomplete leaf, and the mended area of the incomplete leaf can be automatically calculated.

The invention relates to an image recognition method, in particular to an automatic meter-reading image recognition method, and aims at solving the technical problem of low accuracy and proneness to digital recognition error. The automatic meter-reading image recognition method is simple and convenient to use, capable of accurately recognizing dial plate images and high in accuracy. The technical scheme includes the following steps: a, collecting images of a dial plate by an image collecting device; b, roughly positioning a digit indicating image; c, accurately positioning a digit indicating area image; d, accurately positioning a pointer area image; e, preprocessing the images; f, performing digit division; g, performing digit recognition; h, recognizing angle of a pointer. The automatic meter-reading image recognition method is widely used for recognition of digits of the dial plate in a remote meter reading system.

The invention provides a fingerprint minutiae matching method syncretized to global information and a system thereof. The system realizes the entire matching process by an image acquiring unit, an image pre-processing unit, a feature extracting unit, a template storing unit and a feature matching unit, which specifically comprises the following steps: from the feature extracting unit, extracting the feature including the globe information, that is, minutiae handedness, and regarding the minutiae handedness, minutiae information, and minutiae local direction description as the feature to represent the fingerprint; measuring the similarity between the minutiaes by the minutiae handedness and the minutiae local direction description; selecting several pairs of minutiaes having the greatest similarity as an initial dot pair; registering the fingerprint feature and obtaining the corresponding matching fractions with each group of initial dot pair as a reference; selecting the maximum matching fraction in matching fractions as the finial matching fraction; judging whether the input fingerprint feature and the template fingerprint feature are from the same finger based on the final matching fraction, thereby finishing the minutiae matching of the fingerprint.

The invention discloses a convolutional variational auto-encoder neural network-based finger vein identification method and system. The system comprises an image collection module, an image preprocessing module, an image feature extraction module, an image training module and an image identification module. The identification method comprises the steps of obtaining a finger vein image of a to-be-identified user; performing image preprocessing on finger vein image information, and extracting a finger vein region-of-interest (ROI) image; extracting finger vein feature codes in a finger vein ROIthrough the convolutional variational auto-encoder neural network; and inputting the feature codes to a full connection network for performing identification processing, thereby identifying identity information of the to-be-identified user. The finger vein features can be effectively extracted; the noise redundancy is improved; and the identification precision of the finger vein identification system is remarkably improved.

The invention provides a face image completion method based on a self-attention deep generative adversarial network. The method comprises the following steps: constructing a face image completion model comprising an attention recurrent neural network module, a generator network and a discriminator network; carrying out data collection: collecting a large number of face images to form an image set, and dividing the image set into a training set and a test set; carrying out image preprocessing to enable the size of the image to be suitable for processing in a deep learning network; constructing a damaged face image serving as model input; carrying out model training, using a GAN framework and various regularization means to directly train the generator network and the discriminator network at the same time in an end-to-end mode, and when the generator network and the discriminator network reach theoretical Nash equilibrium, completing model training; training the model. Compared with the prior art, the face image complementing method based on the self-attention deep generative adversarial network has the advantage that the complemented face image is better in quality.

The invention discloses a CT image pulmonary parenchyma three-dimensional semantic segmentation method based on a deep neural network. The segmentation method comprises an offline part and an online part. The offline part comprises four steps: preprocessing a data set; Constructing a full convolutional neural network framework; Constructing a GRU cyclic convolutional neural network framework; Network training. The online part comprises the following five steps: preprocessing an image; Extracting and fusing pixel features; Extracting and fusing voxel characteristics; Performing segmented output; Segmentation result evaluation. The feature fusion comprises feature fusion between an encoding layer and a decoding layer and feature fusion between anatomical structure layers. A deep neural network model with a gating circulation unit is designed, and spatial features are extracted by using anatomical structure prior information of a lung to effectively represent an apparent evolution relationship between fault sequences, so that accurate three-dimensional semantic segmentation is carried out on lung parenchyma in a CT image.

The invention discloses a somatosensory-based natural interaction method for a virtual mine. The method comprises the steps of applying a Kinect to acquire gesture signals, depth information and bone point information of a user; carrying out smoothing filtering on images, depth information and bone information of the gesture signals; dividing gesture images by using a depth histogram, applying an eight neighborhood outline tracking algorithm to find out a gesture outline, and identifying static gestures; planning feature matching identification of dynamic gestures by improving dynamic time according to the bone information; triggering corresponding Win32 instruction information by using a gesture identification result, and transmitting the information to a virtual reality engine, respectively mapping the instruction information to the primary keyboard mouse operation of a virtual mining natural interaction system, so as to realize the somatosensory interaction control of the virtual mine. According to the method provided by the invention, the natural efficiency of man-machine interaction can be improved, and the immersion and natural infection represented by the virtual mine can be improved, and the application of the virtual reality and a somatosensory interaction technology can be effectively popularized in coal mines and other fields.

The invention relates to a method for identifying crop diseases and pests based on an Android mobile phone platform. The method comprises the steps that disease and pest pictures are taken through a camera and stored in an SD card of an Android mobile phone; the disease and pest pictures are preprocessed; features of the preprocessed disease and pest pictures are extracted; feature training is carried out on a feature set, and sample set data are trained through an SVM method to obtain a disease and pest diagnosis model; SVM classification is carried out through the disease and pest diagnosis model, a classification and diagnosis result of the diseases and pests is obtained, and prevention and treatment methods are fed back to a mobile phone user. The invention further discloses a system for identifying crop diseases and pests based on the Android mobile phone platform. Through picture preprocessing and feature extraction carried out on the disease and pest pictures, the disease and pest pictures are classified through the SVM learning method to set up the disease and pest diagnosis model, the purpose of identifying the disease and pest pictures is achieved, and the user only needs to take pictures for the diseases and pests in an aligned mode through the mobile phone, and identification efficiency is high.

The invention discloses a camera lens occlusion detecting system and method. The system comprises an image collection module, an image pre-processing module, a background establish module, a high-frequency component extraction module, a generalized image establish module, a suspected occlusion area detection module and an occlusion area determining module, wherein the background establish module is used for acquiring a smooth background image; the high-frequency component extraction module differentiates an initial image and the background image to acquire a high-frequency component distribution graph; the generalized image establish module combines an enhanced image and a pre-processed initial image to establish a generalized image, and performs edge extraction on the generalized image and the generalized image is convolved; the suspected occlusion area detection module compares a convolution result with a preset threshold, and determines that the suspected occlusion area is a candidate occlusion area if the convolution result is less than the preset threshold; and the occlusion area determining module traces the subsequent image pixel value of the suspected occlusion area, and determines that the suspected occlusion area is an occlusion area finally if brightness variations of all the pixels in the area are less than the preset threshold. By using the system and the method, whether the lens is occluded or not can be effectively judged.

The invention discloses a remote damage assessment method and system based on distributed artificial intelligent image recognition. The method comprises the steps that an image collecting device collects external part images of a traffic accident vehicle and sends the external part images to a cloud platform; a vehicle-mounted sensor device acquires collision data information and uploads the collision data information to the cloud platform; an image processing module carries out preprocessing on the collected external part images of the traffic accident vehicle and stores the image preprocessing results into a vehicle damage assessment database; an image feature extraction module extracts features of the external part images according to the image preprocessing results, image matching is carried out on the obtained preprocessing external part image feature information of the traffic accident vehicle and an image base in the vehicle damage assessment database, and an external part damage assessment result of the traffic accident vehicle is obtained through a vehicle external part damage assessment model. By means of the method, on one hand, traffic accident vehicle external part damage assessment can be quickly carried out; on the other hand, by means of image and collision information step-by-step type damage assessment, the damage assessment faults can be reduced, and the precision and efficiency of settlement of claims can be improved.