A diagnostic tool for deep learning similarity models and image classifiers provides valuable insight into neural network decision-making. A disclosed solution generates a saliency map by: receiving a baseline image and a test image; determining, with a convolutional neural network (CNN), a first similarity between the baseline image and the test image; based on at least determining the first similarity, determining, for the test image, a first activation map for at least one CNN layer; based on at least determining the first similarity, determining, for the test image, a first gradient map for the at least one CNN layer; and generating a first saliency map as an element-wise function of the first activation map and the first gradient map. Some examples further determine a region of interest (ROI) in the first saliency map, cropping the test image to an area corresponding to the ROI, and determine a refined similarity score.

A method and system for checking data gathering conditions or image capturing conditions associated with images during AI based visual-inspection process. The method comprises generating a first representative (FR1) image for a first group of images and a second representative image (FR2) for a second group of images. A difference image data is generated between FR1 image and the FR2 image based on calculating difference between luminance values of pixels with same coordinate values. Thereafter, one or more of a plurality of white pixels or intensity-values are determined within the difference image based on acquiring difference image data formed of luminance difference-values of pixels. An index representing difference of data-capturing conditions across the FR1 image and the FR2 image is determined, said index having been determined at least based on the plurality of white pixels or intensity-values, for example, based on application of a plurality of AI or ML techniques.

ADVANCED RESPONSE PROCESSING IN WEB DATA COLLECTION discloses processor-implemented apparatuses, methods, and systems of processing unstructured raw HTML responses collected in the context of a data collection service, the method comprising, in one embodiment, receiving raw unstructured HTML documents and extracting text data with associated meta information that may comprise style and formatting information. In some embodiments data field tags and values may be assigned to the text blocks extracted, classifying the data based on the processing of Machine Learning algorithms. Additionally, blocks of extracted data may be grouped and re-grouped together and presented as a single data point. In another embodiment the system may aggregate and present the text data with the associated meta information in a structured format. In certain embodiments the Machine Learning model may be a model trained on a pre-created training data set labeled manually or in an automatic fashion.

An illustrative image descriptor generation system determines a subset of image descriptors from a plurality of image descriptors that each correspond to a different feature point included within an image. The subset of image descriptors is determined based on geometric proximity, within the image, of respective feature points of the subset of image descriptors to a feature point of a primary image descriptor. The image descriptor generation system then selects a secondary image descriptor from the subset of image descriptors and combines the primary image descriptor and the secondary image descriptor to form a composite image descriptor. Corresponding methods and systems are also disclosed.

Described is a system and method for accurate image and/or video scene classification. More specifically, described is a system that makes use of a specialized convolutional-neural network (hereafter CNN) based technique for the fusion of bottom-up whole-image features and top-down entity classification. When the two parallel and independent processing paths are fused, the system provides an accurate classification of the scene as depicted in the image or video.

An optical readout method for detecting a precipitate (e.g., a precipitate generated from the LAMP reaction) contained within a droplet includes generating a plurality of droplets, at least some which have a precipitate contained therein. The droplets are imaged using a brightfield imaging device. The image is subject to image processing using image processing software executed on a computing device. Image processing isolates individual droplets in the image and performs feature detection within the isolated droplets. Keypoints and information related thereto are extracted from the detected features within the isolated droplets. The keypoints are subject to a clustering operation to generate a plurality of visual “words.” The word frequency obtained for each droplet is input into a trained machine learning droplet classifier, wherein the trained machine learning droplet classifier classifies each droplet as positive for the precipitate or negative for the precipitate.

A driving assistance apparatus includes a gaze detection portion detecting a gaze distribution of a driver for a vehicle, an image acquisition portion acquiring a captured image from an imaging device that captures an image in surroundings of the vehicle, a driver information acquisition portion acquiring driver information that allows identification of the driver for the vehicle, a generation portion generating a personalized saliency map based on the captured image and the driver information, the personalized saliency map that serves as a saliency map for the captured image and that differs depending on the driver, and a determination portion determining whether or not the driver looks at a visual confirmation target in the surroundings of the vehicle by comparing the gaze distribution detected by the gaze detection portion and the personalized saliency map generated by the generation portion.

In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and used—or ignored—in product identification. A great variety of other features and arrangements are also detailed.

Disclosed is a method of analyzing abnormal behavior by using data imaging, including: receiving data to be analyzed as an input, wherein the data to be analyzed is related to a state of a system to be analyzed; converting the inputted data to be analyzed into image data; training a neural network unit with the converted image data as an input; and detecting or predicting abnormal behavior in the system to be analyzed, at the neural network unit, which has received the image data converted from the data to be analyzed as the input and completed training.

A computer-implemented method of handling an emergency incident rcan include receiving information on an emergency incident that includes at least one image of the emergency incident, applying a Convolutional Neural Network (CNN) object recognition and classification process for identifying and marking objects on the at least one image that are related to the emergency incident and that may cause at least one secondary hazardous situation, processing the data relating to the identified and marked objects by applying a deep learning algorithm to the data in a Relational Network (RN) architecture, wherein the image on the basis of the identified and marked objects is correlated to a set of recognized objects in a database for classifying the emergency. A communication network, communication apparatus, and an emergency processing unit are also provided. Embodiments of such machines and systems can be configured to implement embodiments of the method.