The present invention provides a method and a device for detecting interest points in an image. The method includes: acquiring an original input image; performing down-sampling processing on the original input image, so as to obtain a plurality of sampling images with different resolutions; dividing each sampling image into a plurality of small image blocks; performing filtering processing on the plurality of small image blocks in each sampling image in sequence by using Laplacian-of-Gaussian filters, so as to obtain filtered images of the plurality of small image blocks in each sampling image; and acquiring interest points in an image in filtered images of the plurality of small image blocks in each sampling image. The present invention is used for solving the problems of more memory consumption and a low detection speed in the prior art.

A computer-implemented method of recognizing a facial expression of a subject in an input image is provided. The method includes filtering the input image to generate a plurality of filter response images; inputting the input image into a first neural network; processing the input image using the first neural network to generate a first prediction value; inputting the plurality of filter response images into a second neural network; processing the plurality of filter response images using the second neural network to generate a second prediction value; weighted averaging the first prediction value and the second prediction value to generate a weighted average prediction value; and generating an image classification result based on the weighted average prediction value.

A device that includes a model training engine implemented by a processor. The model training engine is configured to select a first sub-string correlithm object and a second sub-string correlithm object from a set of sub-string correlithm objects. The model training engine is further configured to compute a Hamming distance between the first sub-string correlithm object and the second sub-string correlithm object and to compare the Hamming distance to a bit difference threshold value. The model training engine is further configured to determine that the Hamming distance is less than the bit difference threshold value and to compute an average of the first sub-string correlithm object and the second sub-string correlithm object in the n-dimensional space in response to the determination. The model training engine is further configured to train the machine learning model to define the average as a centroid for the first cluster.

A model calculating device calculates a mammary gland normal architecture model that scatters in a fan shape from the nipple toward the greater pectoral muscle with respect to the X-ray image of the breast. An orientation extracting device extracts linear components orientations of a region image texture that form a shape of a shadow in the breast X-ray image using a Gabor filter. A lesion determining device compares the mammary gland orientation in the normal architecture model calculated by the model calculating device and the orientation extracted by the orientation extracting device with respect to a region of interest in the X-ray image of the breast including architectural distortion candidates of the mammary gland detected by a preprocessing device to calculate a feature quantity based on a difference between the orientations and determines whether the candidates are an architectural distortion of the mammary gland based on the feature quantity.

A method for operating an image processing device coupled to a color camera and a depth camera is provided. The method includes receiving a color image of a 3-dimensional scene from a color camera, receiving a depth map of the 3-dimensional scene from a depth camera, generating an aligned 3-dimensional face mesh from a plurality of color images received from the color camera indicating movement of a subject's head within the 3-dimensional scene and form the depth map, determining a head region based the depth map, segmenting the head region into a plurality of facial sections based on both the color image, depth map, and the aligned 3-dimensional face mesh, and overlaying the plurality of facial sections on the color image.

Object detection and classification across disparate fields of view are provided. A first image generated by a first recording device with a first field of view, and a second image generated by a second recording device with a second field of view can be obtained. An object detection component can detect a first object within the first field of view, and a second object within the second field of view. An object classification component can determine first and second level classification categories of the first object. A data processing system can create a data structure indicating a probability identifier for a descriptor of the first object. An object matching component can correlate the first object with the second object based on the descriptor of the first object, the probability identifier for the descriptor of the first object, or a descriptor of the second object.

A method for recognizing different object-categories within images based on texture classification of the different categories, which is implemented in an electronic device, includes extracting texture features from block images segmented from original images according to at least one Gabor filter; determining a grayscale level co-occurrence matrix of each block image according to the texture features; calculating texture feature statistics of each block image according to the grayscale level co-occurrence matrix; training and generating an object recognition model using the texture features and the texture feature statistics; and recognizing and classifying at least one object in original image according to the object recognition model.

An image processing apparatus comprises: a model obtaining unit configured to obtain a learned model that has learned, based on a position of a predetermined feature point, a contour of a target in an image obtained by capturing the target; an image obtaining unit configured to obtain an input image; a position obtaining unit configured to obtain a position of an input point input on the input image by a user; a normalization unit configured to obtain a normalized image generated by coordinate-transforming the input image such that the position of the input point matches the position of the predetermined feature point in the learned model; and an estimation unit configured to estimate the contour of the target in the input image using the normalized image and the learned model.

Disclosed are systems and methods for improving interactions with and between computers in computerized security and content monitoring, hosting and providing devices, systems and/or platforms. The disclosed systems and methods provide a novel framework that adaptively distinguishes between known people versus unknown people based on a dynamically applied, anonymous facial recognition methodology. The disclosed framework provides such functionality by recognizing faces within captured images without storing any information or annotations regarding or revealing the captured person's identity. The framework is configured to adaptively learn to distinguish between faces seen for the first time and faces it has previously seen by locally processing a captured image and only sending face embeddings to a network location for future comparisons of subsequently, anonymously captured images.

The present invention discloses a credible fruit traceability method and device based on fruit texture atlas and blockchain. According to the present invention, images of fruit pedicel part and fruit navel part of a single fruit are obtained, and the images are grayed and normalized to be converted into rectangular images; features are extracted from the rectangular images, respectively, and are encoded to obtain a fruit pedicle feature code table and a fruit navel feature code table; the two feature code tables are subjected to a merging operation to obtain a combined bidirectional feature code table, thus forming a unique fruit texture atlas. By processing the fruit texture atlas, the fruit texture atlas information and related information are stored on the blockchain. The user uses the same algorithm to obtain a fruit texture atlas of a fruit to be inspected through a smart terminal, the fruit texture atlas is processed and then is compared with the information on the blockchain for verification, so as to achieve the purpose of credible traceability. The present invention realizes the uniqueness and convenience of fruit identification, solves the problem of information tampering by evidence storage on the blockchain, and achieves the purpose of credible traceability.