22 results about "Aspect ratio (image)" patented technology

Systems and methods for image processing (e.g., image extension or image uncropping) using neural networks are described. One or more aspects include obtaining an image (e.g., a source image, a user provided image, etc.) having an initial aspect ratio, and identifying a target aspect ratio (e.g., via user input) that is different from the initial aspect ratio. The image may be positioned in an image frame having the target aspect ratio, where the image frame includes an image region containing the image and one or more extended regions outside the boundaries of the image. An extended image may be generated (e.g., using a generative neural network), where the extended image includes the image in the image region as well as generated image portions in the extended regions and the one or more generated image portions comprise an extension of a scene element depicted in the image.

The invention relates to a Badam sorting method and device based on an X-ray image, and the method comprises the steps: obtaining an original X-ray image, and carrying out the preprocessing of the original X-ray image; processing the preprocessed X-ray image to obtain an image to be sorted; a density defect fusion descriptor, a penetrating empty shell recognition descriptor, a structure and texture stability descriptor and a special-shaped impurity recognition descriptor are extracted from each to-be-sorted image, and the density defect fusion descriptor fuses a gray average value, a gray standard deviation and a low-gray connected region proportion; the penetrable empty shell recognition descriptor is fused with density gradient and packing ratio, the structure and texture stability descriptor is fused with contour area and roundness, and the special-shaped impurity recognition descriptor is fused with length-width ratio, pixel energy and local texture ambiguity; and obtaining a sorting result. Compared with the prior art, the method has the advantages of high classification precision and the like.

Problem: high-precision detection of impersonation of a person using a planar object such as a photograph. Solution: imaging means 11 that images a plurality of frames of the verification target at different angles; feature detection means 14 that detects the aspect ratio of the face of the verification target, i.e., the ratio of the vertical length to the horizontal length, from each of the plurality of frames of images imaged by the imaging means 11; and impersonation detection means 14 that detects impersonation of a person using a planar object based on the aspect ratio of the face of the verification target imaged at different angles.

This disclosure provides a character recognition method, apparatus, electronic device, and storage medium. The character recognition method includes: acquiring an image of a target character to be tested, wherein the target image includes at least one character to be tested; extracting and determining the grayscale value and aspect ratio of each character to be tested based on the image of the target character to be tested; extracting and determining the directional gradient, geometric invariant moments, and gray-level co-occurrence matrix of each character to be tested based on the grayscale value; determining the geometric features of each character to be tested based on the aspect ratio; determining the edge features of each character to be tested based on the directional gradient and the geometric invariant moments; determining the texture features of each character to be tested based on the gray-level co-occurrence matrix; inputting the geometric features, the edge features, and the texture features into a character recognition model; and outputting the recognition result of each character to be tested through the character recognition model.

The present invention relates to a body fluid test method, comprising: a step for identifying the ROI region of each sperm in each of n set image frames; reducing the image brightness of each of the n image frames by a set value; a step of creating an accumulated image frame in which the images of each sperm in the n image frames are accumulated; a step of confirming a movement path region of each sperm in the accumulated image frame; for each sperm, calculating the width of the moving path area, and judging the activity according to the calculated width; and calculating the aspect ratio of a rectangle surrounding the movement path region for each sperm, and determining the straightness according to the calculated aspect ratio.

The disclosed approach performs image compression using a variational auto-encoder that is capable of greater compression than conventional approaches while maintaining high fidelity of the decompressed image. Examples persist a bottleneck layer output of a variational auto-encoder into a compressed image in the form of potential tensors. The potential tensor is decompressed into a restored image in the pixel space by a variational self-decoder. In some examples, different encoder / decoder pairs are trained on a particular image type based on feature attributes. For example, maps have lines that are narrower compared to their length (e.g., with high aspect ratios), which differ from features within photographs of persons and scenes. Some examples utilize contrast language image pre-training (CLIP) and / or bootstrap language image pre-training (BLIP) models to store inserts, each of which is associated with a compressed image to enable a natural language search of a set of compressed images without requiring decompression.

The invention discloses a network-based rail B-display image recognition method, which belongs to the field of railway track flaw detection and deep learning, and comprises the following steps: 1, acquiring a rail B-display image, dividing the B-display image into five types of labels, namely a rail end label, a rail head nuclear flaw label, a normal screw hole label, an abnormal screw hole label and a lead hole label, and constructing a data set after performing data enhancement on small sample types; 2, a data set is put into the model for training, an attention module is embedded into the model, the sensing ability of key features is enhanced through channel re-calibration, and the detection precision of small target damage is improved; and 3, aiming at a thin and long target with an extreme aspect ratio, an EIoU loss function is adopted to optimize bounding box regression, and the positioning precision and the convergence speed of the model in a complex form are remarkably improved. According to the invention, fine defects such as rail head nuclear injury, abnormal screw holes and the like can be effectively identified, the omission ratio and the false detection ratio are reduced, intelligent identification and automatic analysis of B-display images are realized, the manual dependence is greatly reduced, and the detection efficiency and the railway operation safety are improved.

The invention relates to the technical field of image enhancement, in particular to a blade scratch recognition method based on image enhancement, which comprises the following steps of: defining a texture sliding window with the size of N * N according to a to-be-detected blade grayscale image, and controlling the texture sliding window to carry out pixel-by-pixel traversal on a pixel coordinate system of the to-be-detected blade grayscale image, and calculating and generating a local entropy value. According to the method, the fused matrix is processed through morphological closed operation, the discontinuous high-response area is connected through the structural elements, internal holes are filled, the scratch fracture phenomenon caused by uneven illumination or metal reflection is repaired, and the completeness and continuity of the defect form are ensured. And performing connected domain marking based on a binary mask, extracting geometric parameters of an external rectangle, strictly screening the connected domains according to a length-width ratio form standard, and removing non-strip interference noise such as spots and pits, so that high-precision positioning of fine scratches on the surface of the blade is realized.

This invention relates to a method and apparatus for sorting almonds based on X-ray images. The method includes: acquiring original X-ray images and preprocessing them; processing the preprocessed X-ray images to obtain images to be sorted; extracting density defect fusion descriptors, penetrating shell identification descriptors, structure and texture stability descriptors, and irregular impurity identification descriptors from each image to be sorted. The density defect fusion descriptor incorporates the mean gray level, gray level standard deviation, and proportion of low-gray-level connected regions; the penetrating shell identification descriptor incorporates density gradient and fill ratio; the structure and texture stability descriptor incorporates contour area and roundness; and the irregular impurity identification descriptor incorporates aspect ratio, pixel energy, and local texture ambiguity. The sorting result is then obtained. Compared with existing technologies, this invention has the advantages of high classification accuracy.

This invention relates to a method and apparatus for object detection and determining training samples for object detection. The method, when dividing positive and negative samples, determines positive samples of target boxes based on the aspect ratio of the target boxes in the training image. Furthermore, when the aspect ratio of a target box is large, a first preset threshold inversely proportional to the aspect ratio is set. This results in a smaller first preset threshold when the aspect ratio of the target box is large. Using the intersection-union ratio (IUU) of candidate boxes and target boxes, along with the first preset threshold, can also effectively determine whether a candidate box is a positive sample, avoiding missed detections. This lays the foundation for training an object detection model based on positive and negative samples of target boxes in the training image. The trained object detection model can better learn the position and feature information of the object to be detected, reducing the missed detection rate of objects with large aspect ratios, thereby improving the accuracy of object detection.

The application discloses an aragonite whisker preparation method and system based on image recognition and multi-model prediction, and comprises the following steps: in each sampling period, a microscopic image of reaction slurry is subjected to mask extraction, skeleton thinning, cross point breaking and ellipse fitting processing, an average observation vector of crystal size is decoupled and output, a 2D-PBM is input with estimated liquid phase ion concentration, a two-dimensional growth kinetics model is combined, and a posterior state vector at the current moment is obtained; an ESN proxy model is used to replace the 2D-PBM, and the crystal morphology evolution trajectory in the future time domain is deduced within the current sampling period; air inlet component fluctuation is fed forwardly compensated, and adjustment instructions for temperature and air inlet flow are output and executed. The application realizes direct and real-time closed-loop control on the aspect ratio of acicular crystals, suppresses morphology degradation caused by impurity fluctuation, and improves product quality and aragonite phase purity.

The embodiment of the invention relates to the technical field of image processing, in particular to a sample balancing method suitable for small target detection, and the method comprises the steps: obtaining a plurality of anchor frames and truth value bounding boxes for a target object in a feature map of a target image, the scale parameters and aspect ratio parameters of different anchor frames being different, and the truth value bounding boxes being different; pixel points occupied by the target object in the target image are smaller than a preset value; based on the position coordinates of the truth value bounding box and the position coordinates of the anchor frames, respectively calculating detection quantities between the truth value bounding box and the anchor frames; wherein the detection quantity is used for measuring the similarity degree between the anchor frame and the true value bounding box; dividing the plurality of anchor frames into a positive training sample, a negative training sample and an invalid sample based on the detection quantity between the true value bounding box and the plurality of anchor frames; and outputting a positive training sample and a negative training sample, wherein the positive training sample and the negative training sample are used for subsequent classification operation and regression operation of the target object. According to the method, the small target detection capability can be greatly improved.

A procedure for detecting vehicle damage on a target vehicle, comprising the following: Subdivide (S101) the overall appearance of the target vehicle into N predefined blocks, where N is a positive integer; Performing an image capture (S102) to obtain original images; Performing vehicle part recognition (S103) for each of the original images to obtain a vehicle part position recognition result; Performing a damage assessment (S105) for each of the original images to obtain a damage assessment result; and Merging (S106) the vehicle part position detection result with the damage detection result to obtain a vehicle part damage result for the target vehicle, characterized by the fact that an image acquisition is performed for each of the N blocks according to a predefined image acquisition model (S102) to obtain N original images corresponding to the N blocks; wherein the image acquisition model further comprises: performing an image acquisition for the N blocks of the target vehicle, each from a preset recording angle, in order to obtain N original images, each with an aspect ratio a:b, a vehicle part recognition is performed for each of the N original images (S103), Each of the N original images is cropped into M sub-images of a predefined size according to a predefined cropping model (S104), where M is a positive integer; The cropping model includes the following: Dividing each of the N original images horizontally into a equal parts and vertically into b equal parts to obtain a × b sub-images, where a × b = M, and A damage detection (S105) is performed for each of the N original images and its corresponding M sub-images.

[Problem] To accurately detect spoofing of a person that is based on a photograph or other planar objects. [Solution] Involving the following: an imaging means 11 for capturing images in a plurality of frames of a subject to be authenticated from different angles; a feature detection means 14 for detecting an aspect ratio, which is the ratio between the vertical length and horizontal length of the face of the subject, from each of the frame images captured by the imaging means 11; and a spoofing detection means 14 for, on the basis of the aspect ratio of the face of the subject captured from different angles, detecting spoofing of a person based on a planar object.

This invention provides a method for rapidly testing the two-dimensional shape characteristics of aggregates, relating to the field of civil engineering materials. The method includes: sieving to obtain a sufficient quantity of aggregates with a specified particle size; acquiring image information of the aggregates using an image acquisition device; processing the aggregate images using grayscale conversion, threshold segmentation, and binarization methods to facilitate subsequent calculations; obtaining the corresponding isoellipse information of the aggregate images by calculating the covariance matrix, further obtaining information such as the aspect ratio of the isoellipses; and calculating the perimeter and area of ​​polygons using contour edge recognition methods and Green's formula to obtain roundness values. This method can not only process aggregate information in large batches simultaneously to obtain the key two-dimensional shape characteristics of the aggregates in that batch, but also has advantages such as simple operation, short testing cycle, and accurate results, providing an efficient and convenient technical means for analyzing the impact of aggregate morphology on the performance of cement concrete and asphalt concrete.

This invention provides a method for optimizing noise in concrete crack outlining images, comprising: acquiring crack images and sequentially converting them to grayscale and adaptive binarization to obtain black-and-white binary images; applying a Gaussian blur algorithm to blur the black-and-white binary images to obtain processed black-and-white crack images; using the Canny operator to outline the processed black-and-white crack images to obtain outlined images; using the findCountours function to extract all outline frames from the outlined images to obtain individual outline frames; calculating the minimum bounding rectangle of each individual outline frame; analyzing the outline vector and aspect ratio of the minimum bounding rectangle; and, based on the analysis, removing outlines that do not meet the standards to obtain the final crack outlining image. The concrete crack outlining image noise optimization method provided by this invention can effectively identify and eliminate large-area image noise and minute image noise.

The embodiment of the invention provides an image processing method and device, electronic equipment and a storage medium, and relates to the technical field of image processing, and the method comprises the steps: obtaining a to-be-processed image and a target aspect ratio; determining an image processing mode for the to-be-processed image according to the target aspect ratio and an initial aspect ratio of the to-be-processed image; in the expansion mode, generating an expansion background on the outer side of the image edge of the to-be-processed image based on the resolution, the initial aspect ratio and the target aspect ratio of the to-be-processed image to obtain a target image; in the cutting mode, cutting the to-be-processed image based on the resolution of the to-be-processed image, the initial aspect ratio, the target aspect ratio and the position information of the foreground target in the to-be-processed image to obtain a target image; wherein the aspect ratio of the target image is the target aspect ratio. According to the scheme, the electronic equipment can realize automatic conversion of the aspect ratio of the image, and can meet the requirement of quickly converting the aspect ratio of the image in batches.

The article to which the design pertains in this design registration application (hereinafter referred to as "the Application") is an image generation GUI using AI technology. The image diagram shows a screen that displays a list of images in order to visually recognize the history of how the generated images were created. The image diagram shows a state in which a total of five images have been generated by performing a process four times in which one image with a 1:1 aspect ratio is generated by inputting prompts, and then another image with a 1:1 aspect ratio is generated based on that image by inputting prompts. The number of images generated, the aspect ratio, and other conditions of the generated images vary depending on the content of the prompts entered and the number of times the prompts are entered.

This disclosure provides a method, device, equipment, and storage medium for detecting and warning of driver fatigue. The method includes: reconstructing an image to be detected using a low-rank approximation method to obtain a reconstructed image to be detected; extracting facial features from the reconstructed image to be detected, and calculating the current eye aspect ratio, current mouth aspect ratio, and current head pitch angle using the facial features; determining the magnitude of a dynamic deviation operator based on the degree of change between the current eye aspect ratio and the original eye aspect ratio, and the degree of change between the current mouth aspect ratio and the original mouth aspect ratio; combining the values ​​of the current eye aspect ratio and the current mouth aspect ratio using the dynamic deviation operator to obtain a dynamic weighted sum of eye and mouth; determining the driver's pitch angle state, and if the current head pitch angle is greater than a pitch angle threshold, determining driver fatigue; otherwise, determining the driver's eye and mouth opening / closing state, and if the dynamic weighted sum of eye and mouth is greater than a combined eye and mouth threshold, determining driver fatigue.

The application discloses a method for determining the aspect ratio of an image batch, wherein the resolution of the image batch is denoted as (h, w), the aspect ratio of the image batch is denoted as P, P=h / w; the resolution of each image in the batch is obtained, the resolution of the i-th image is denoted as (Hi, Wi), and the aspect ratio of the i-th image is denoted as Ri, Ri=Hi / Wi; and the following condition is met: the application has the advantages that the waste of computing power resources can be reduced.

This invention discloses a geometry-guided method and system for identifying and sorting objects in a virtual-to-physical migration environment. The method includes: generating a synthetic reference image that ignores material photometric properties using geometric abstract rendering based on the object's CAD model; performing isotropic scaling and filling on a real-time acquired physical object image while maintaining the original aspect ratio, and outputting a standardized image; extracting feature vectors from the synthetic reference image and the standardized image using the same convolutional neural network; adjusting the batch normalization layer statistical parameters in the convolutional neural network online using at least one real-time acquired physical image to align the feature distributions of the synthetic and physical domains; calculating feature similarity and outputting the recognition result. This invention, through subtractive geometric prior rendering, affine invariant preprocessing, and single-sample dynamic statistical calibration, can be deployed on edge computing devices to meet high-speed sorting cycle requirements.

The article to which the design pertains in this design registration application (hereinafter referred to as "the Application") is an image generation GUI using AI technology. The image diagram shows the state in which five images with a 1:1 aspect ratio have been generated by inputting prompts. The user can generate further images, as shown in the changed image diagram, by clicking the "edit" button located below the generated images and entering additional prompts. The changed image diagram shows the state in which five images have been generated based on the first image generated and the additional prompts. In each generation phase, the number of images generated, the aspect ratio, and other conditions of the generated images will vary depending on the input prompts, so the aspect ratio is not limited to 1:1 and the number of generated images is not limited to five.