100 results about "Image quality analysis" patented technology

The present invention relates to a computer-implemented method of performing image quality analysis on images from an imaging examination, including: displaying an imaging examination; performing a quality review of the images; performing a quality analysis on data from the imaging examination and on the images; receiving image quality analysis from the user on the data and the images and storing the image quality analysis in at least one database; saving data from the image quality analysis on at least one key image of the images, using computer-generated standardized annotation and mark-up, or graphical data input, or speech data, using a computerized tool, and saving the data as annotated image data in the at least one database; and transferring the annotated image data to at least one quality assurance database with linking to images from the imaging examination.

A method for automated image quality based diagnosis of a document printing system is disclosed. The method comprises receiving image data to be printed on a document; printing an image on the document based on the image data; scanning the printed image on the document with a sensor; analyzing the scanned printed image with an image quality analysis module to identify one or more defects in the printed image; automatically generating test pattern image data based on the one or more identified defects; and printing and analyzing a test pattern image based on the test pattern image data.

A document processing system and method for using image quality to sort documents. The document processing system comprises: a document sorting system that designates a destination pocket for each document based on data gathered from each document; a document imaging system that captures an image of each document; and an image quality analysis system that analyzes each image and causes any document having an unacceptable image to be redirected to an unacceptable destination pocket.

The invention is a biometric system based on iris texture analysis, which overcomes the defects in the prior art that lack the support of iris image quality analysis mechanism and cannot complete the evaluation of iris texture image quality. The invention acquires iris texture images, automatically locates iris, evaluates and analyzes the quality of iris texture images, automatically tracks and detects living iris, standardizes polar coordinate transformation of iris analysis area, demodulates and expresses iris texture features, and generates feature code IrisID by quantization coding. Encoding IrisID similarity measurement, similarity measurement judgment and other steps are realized. The invention realizes the basic characteristic requirements of an ideal system: automaticity, non-invasiveness, friendly man-machine operation interface and high-quality imaging image; no correlation between geometric affine transformation and nonlinear affine deformation; no dependence on external imaging conditions ; Random probability distribution coding; High-precision false acceptance rate and false rejection rate performance.

In a method and magnetic resonance (MR) imaging apparatus for reducing artifacts due to resonance frequency offsets in a diagnostic MR image, a number of MR scout images of a portion of a subject containing a region of interest (ROI) are generated respectively using different radio frequency (RF) excitation frequencies. Each of the MR scout images has an identifiable image quality in the ROI. The MR scout images are analyzed as to the image quality in the ROI to identify one of the MR scout images having the best image quality in the ROI. An MR diagnostic image is then generated of the portion of the subject containing the ROI, using the RF excitation frequency that was used to generate the MR scout image having the best image quality in the ROI.

A virtual tech rep system that can assist in reducing service call visits and customer complaints by readily analyzing image quality of an output image device, such as a copier or printer. The system generates a hardcopy test pattern output from the copier or printer and then scans the test pattern using either the platen of the digital copier or an external scanner to form a digital raster image. Test targets in the digital raster image are then determined using pattern recognition software and image quality analysis is then performed on the test targets based on the sensitivity of the human visual system. It is preferable that the image quality analysis is based on human vision systems rather than a direct comparison between original and printed images as many differences may go unnoticed by a human viewer whereas other types of differences may be readily noticed, even if only slight. The system optionally sends the test results and possibly part or all of the scanned test pattern to a service or diagnostic facility (remote or local) for further analysis when potential defects are identified. This process may be performed at start-up or automatically initiated after a predetermined number of operating cycles or hours of use have been attained.

Accommodating the data needed to process checks for payment under the Check Clearing for the 21^st Century Act by using expanded fields of a financial data file. The financial data file can comprise the complete, original MICR data from an original or substitute paper check. The financial data file can comprise truncated data in conventional fields F1-F7 and untruncated data in expanded fields F10-F11. The financial data file further can comprise a result from an image quality analysis performed on an electronic image of the check. The untruncated MICR data and the electronic check image can be used to correct errors in the financial data file and to present the check for payment via a substitute check or an electronic image cash letter. The truncated MICR data can be used to electronically process the check via conventional means.

Efficiently assessing the quality of an electronic check image by determining whether the check image is suitable for image quality analysis prior to performing the image quality analysis. A check processing module of a check processor can determine whether the check image is suitable for image quality analysis by validating certain tags in the image. For example, such validation can include determining whether the check image includes certain mandatory tags and whether any optional tags present in the image are valid. The check processing module can determine that the check image is not suitable for image quality analysis if it does not include the mandatory tags or if it includes any invalid optional tags. The check processing module can assign a failure value to any check image that is not suitable for image quality analysis. The failure value can indicate a reason for the unsuitability of the check image.

Image analysis includes: determining, using one or more processors, an image quality score associated with an image, including: determining a foreground and a background in the image; calculating a set of one or more characteristic parameters of the image based on the determined foreground and background; calculating the image quality score based at least in part on the set of characteristic parameters, wherein calculating the image quality score comprises using an image quality computation model that has been pre-trained; and in response to a search query, generating a set of search results that includes a set the images, wherein inclusion of the images or ranking of the search results is based at least in part on image quality scores associated with the set of images.

The invention discloses a circle detection method which comprises the following steps: carrying out edge detection on an image to obtain an edge point set of the image; analyzing the edge point set of the image to obtain a quality analysis result of the image; selecting a circle detection algorithm based on the quality analysis result of the image; and using the selected circle detection algorithm to carry out circle detection on the image. The invention also discloses a device for implementing the circle detection method. By carrying out quality analysis on the image before circle detection and selecting different circle detection algorithms to perform circle detection based on the quality of the image, the invention can effectively balance the two indices, namely the circle detection efficiency and the circle detection accuracy, thereby simultaneously ensuring the circle detection accuracy and improving the circle detection efficiency so as to realize high-speed and high-accuracy circle detection.

The invention discloses a human face feature recognition method combined with image quality analysis and metric learning. The method comprises the following steps: processing a human face image, and then adding the processed human face image into a convolution neural network to train so as to acquire the primary feature; obtaining a quality quantized value of the human face image according to the norm of the primary feature; adding a full-connection parameter layer to perform dimension-reduction processing on the primary feature to obtain the final feature; taking the quality quantized value of the human face image as an additional weight information to obtain the weighted mean value according to the final feature, and adding the weighted mean value into the training to obtain a loss function of the metric learning; supervising the training procedure through the loss function to obtain the final parameter of the convolution neural network; taking the final parameter as the final human face feature extraction module and performing the human face feature recognition on the human face image. The quantized value of the image quality can be acquired by using few calculations, and a unified quantization standard is formulated according to the norm value of the human face feature; the network presentation skill is improved, and the adaptability of the network to the low-quality image is enhanced.

The invention provides a human face gender recognition method based on multi-parameter index weighting. According to the method, through tracking the human face of the same person in a video sequence, a plurality of human face images of the same person are collected; the human face image quality analysis is carried out on the collected human face images; the human face image quality analysis results are used as human face gender recognition accuracy weights for calculating human face gender confidence values subjected to image analysis correction; in addition, the human face gender confidence values of the human face images of the same person are subjected to index weighting operation; and the human face gender is finally judged out according to the calculation results. The human face gender recognition method has the advantages that the gender of a certain person is judged by using a plurality of human faces in the video sequence, so the problem that when a single static picture is taken for human face gender recognition, the interference by in-site environment is greater is solved; and in addition, the problem of recognition accuracy interference due to in-site complicated environment is solved through human face image quality analysis and index weight operation.

The invention relates to a detection system and method for dynamic positioning precision of a POS (point of sale) system. The detection system comprises a tracking measurement device, a control device, a measurement cooperative target and a time service device, wherein the measurement cooperative target is mounted on a carrier according to placement parameters between the measurement cooperative target and the to-be-detected POS system; the motion state of the carrier where the measurement cooperative target is located is tracked, and data, measured by the tracking measurement device and the POS system, of the carrier where the measurement cooperative target is located are acquired; overall locus and point position comparison is performed on the data measured by the tracking measurement device and the POS system and the dynamic positioning precision of the POS system is determined. The problem of inaccurate detection precision caused by adoption of error estimation and imaging quality analysis in POS system precision detection at present is solved. The system and the method contribute to completion of a dynamic error model of a mobile measurement system, provide a basis for establishment of a unified sensor placement parameter calibration standard, play a role in promoting development of the mobile measurement technology and have important theoretical significance and application value.

A system and method for automated image analysis selects a Region Of Interest (ROI) within a frame, suitable for subsequent Quantitative Intima Media Thickness (QIMT) analysis. Presently, a time consuming manual analysis by a highly trained technician is required to select the ROI within the frame for subsequent automated analysis. The automated image analysis provides an immediate and accurate identification of the ROI within the selected frame. In one embodiment, the automated image quality analysis may be directed to an ultrasound image of the carotid artery.

The invention discloses a face attendance checking method, device and equipment based on self-learning and a computer readable storage medium. The method comprises the following steps: carrying out face image quality analysis on continuous frame number image data to obtain a plurality of frames of to-be-identified face images, carrying out feature point positioning on the to-be-identified face images, extracting a face feature vector in each frame of to-be-identified face image through a preset convolutional neural network model, and storing the face feature vectors in a face feature list; clustering the face feature list to obtain a face feature matrix; carrying out matching analysis on the face feature vectors of each row in the face feature matrix by adopting a pre-constructed KNN modelto obtain a matching result of each face feature vector in each row, and storing the matching result into an identification similarity matrix; and according to the recognition similarity matrix, a face attendance result is obtained, and face recognition is carried out on multi-person multi-frame images by adopting an image quality analysis method in combination with a face feature clustering method, so that the face recognition precision in the face attendance process can be effectively improved.

The invention provides a method for correcting the brightness and the chrominance of an LED display screen and a mobile communication terminal used by the same. According to the method, correction software is installed in the mobile communication terminal and sends, after a connection is established between the mobile communication terminal and an LED display screen control system, a command to the LED display screen control system in order to control the LED display screen to display frames, such as a color frame for imaging quality analysis, a color frame for correction and the like; and a camera module of the mobile communication terminal captures displayed frames and sends images of the captured frames to the correction software to be processed in order that the exposure of the camera module is adjusted and a brightness and chrominance correction coefficient of the LED display screen is generated. The method may correct the brightness and the chrominance of the LED display screen by using the mobile communication terminal such as a cell phone, prevents a user of the LED display screen from extra purchasing expensive correction equipment, and has advantages of good convenience in use, short correction time, and high efficiency.

The invention provides a HUD (Head Up Display) image testing system and method. The testing system comprises a programmable controller connected with a testing host, a first motion device and a second motion device connected with the programmable controller, a HUD host connected with the first motion device, and a CCD image gatherer connected with the second motion device. The testing host sends a testing command and an image acquisition control command to the programmable controller to make the programmable controller control the first motion device and the second motion device, so that the two motion devices drive the HUD host and the CCD image gatherer to reach a position that is identical to an actual vehicle HUD host installing position and also reach a position of the eyes when a driver views HUD images. The testing host conducts image visual field analysis, image quality analysis, image dimension analysis and image color and brightness analysis on the HUD images to complete an image test. In this way, range, image quality, dimension, color and brightness of the HUD images are automatically tested, the testing efficiency is high, and the testing precision is high.

The disclosure, which belongs to the technical field of image processing, relates to an image quality analysis method and apparatus. The method comprises: gradient extraction is carried out on a to-be-processed image to obtain a gradient image and the gradient image is inputted into a preset convolutional neural network; an edge feature of the gradient image is processed according to a plurality of pre-trained convolution kernels in the preset convolutional neural network; and on the basis of a matching degree between the edge feature of the gradient image and a preset image edge feature, an image quality of a to-be-processed picture is determined. With the method, the image quality of the to-be-processed image is analyzed by using the convolutional neural network, thereby improving the accuracy and efficiency for determining the image quality of the to-be-processed image.

The present invention provides an improved ultrasound imaging system arranged to evaluate a set of acquired 3D image data in order to provide a compounded 3D image of a fetus irrespective of its position and movement. This is achieved by providing an ultrasound imaging system comprising: an ultrasound probe having an ultrasound transducer array operable to acquire at different look directions a plurality of three dimensional (3D) ultrasound image frames of a volumetric region comprising a fetus; a compound image memory for storing the acquired plurality of the 3D ultrasound image frames and an articulated fetal model with a common fetal structure; an ultrasound image processor responsive to the plurality of 3D ultrasound image frames, said processor comprising a fetal segmentation unit arranged to segment each 3D image frame based on the articulated fetal model thereby providing a plurality of spatially related 3D images of the volumetric region; and an image quality analyzer coupled to the segmentation unit and arranged to determine, based on the articulated fetal model, an overall confidence value of the plurality of the 3D images, said image quality analyzer is further arranged to compare the overall confidence value with an image compounding threshold.

The invention discloses a non-inductive attendance checking method, device and equipment and a computer readable storage medium, and the method comprises the steps: carrying out the face feature pointpositioning of images of continuous frames, extracting the face features of each frame of image through a convolutional neural network model, and storing the face features in a face feature list; clustering the face feature list to obtain a face feature matrix; carrying out face image quality analysis on the face features in the face feature matrix; obtaining an image quality value correspondingto the human face feature, constructing a quality analysis matrix, matching the human face feature in the human face feature matrix with an original human face feature stored in a preset original human face database, obtaining a matching result of the human face feature, and storing the matching result in an identification similarity matrix; and obtaining a face attendance result according to thequality analysis matrix and the recognition similarity matrix, and performing face recognition on the multi-person multi-frame image by adopting an image quality analysis method in combination with aface feature clustering method, so that the face recognition precision in the face attendance checking process is effectively improved.