Provided in the present invention are a method and apparatus for processing a block to be processed of a urine sediment image. The method comprises: calculating a variable number of local feature vectors of a block to be processed, wherein the local feature vector is a vector representing a feature of a local location of the block to be processed; classifying the variable number of local feature vectors into a fixed number of clusters so as to obtain a statistical histogram vector of the fixed number of clusters of the block to be processed, wherein the statistical histogram vector reflects the statistical distribution of the variable number of local feature vectors in the fixed number of clusters; and taking the statistical histogram vector as a feature in a feature set of block processing and processing the block to be processed.

A machine vision system and method uses captured depth data to improve the identification of a target object in a cluttered scene. A 3D-based object detection and pose estimation (ODPE) process is use to determine pose information of the target object. The system uses three different segmentation processes in sequence, where each subsequent segmentation process produces larger segments, in order to produce a plurality of segment hypotheses, each of which is expected to contain a large portion of the target object in the cluttered scene. Each segmentation hypotheses is used to mask 3D point clouds of the captured depth data, and each masked region is individually submitted to the 3D-based ODPE.

An object authentication device includes a speech recognition unit configured to obtain candidates for a speech recognition result for an input speech and a likelihood of the speech as a speech likelihood, an image model generation unit configured to obtain image models of a predetermined number of candidates for the speech recognition result in descending order of speech likelihoods, an image likelihood calculation unit configured to obtain an image likelihood based on an image model of an input image, and an object authentication unit configured to perform object authentication using the image likelihood, wherein vocabularies predicted through speech recognition are categorized and the image model is formed in association with a category.

An image processing method for an image recognition using teacher data of a recognition target, the method including: designating a mask designation area which is at least a part of a portion other than a specific characteristic portion in an image of the teacher data of the recognition target; and generating masked teacher data by masking the designated mask designation area of the teacher data of the recognition target, so that variety of teacher data can be increased without any unwilling bias or deviation.

An object authentication device includes a speech recognition unit configured to obtain candidates for a speech recognition result for an input speech and a likelihood of the speech as a speech likelihood and an image model generation unit configured to obtain image models of a predetermined number of candidates for the speech recognition result in descending order of speech likelihoods, wherein the image model generation unit initially performs retrieval from an image model database storing the image models when the image models for the candidates for the speech recognition result are generated and generates an image model from information acquired from a network if the image model is not stored in the image model database.

The described positional awareness techniques employing visual-inertial sensory data gathering and analysis hardware with reference to specific example implementations implement improvements in the use of sensors, techniques and hardware design that can enable specific embodiments to provide positional awareness to machines with improved speed and accuracy.

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 test image; determining, with an image classifier, an image classification of the test image; determining, for the test image, a first activation map for at least one model layer using the determined image classification; determining, for the test image, a first gradient map for the at least one model layer using the determined image classification; and generating a first saliency map as an element-wise function of the first activation map and the first gradient map.

A framework is provided for associating dense images with topics. The framework is trained utilizing images, each having multiple regions, multiple visual characteristics and multiple keyword tags associated therewith. For each region of each image, visual features are computed from the visual characteristics utilizing a convolutional neural network, and an image feature vector is generated from the visual features. The keyword tags are utilized to generate a weighted word vector for each image by calculating a weighted average of word vector representations representing keyword tags associated with the image. The image feature vector and the weighted word vector are aligned in a common embedding space and a heat map is computed for the image. Once trained, the framework can be utilized to automatically tag images and rank the relevance of images with respect to queried keywords based upon associated heat maps.

An image representation method and processing device based on local PCA whitening. A first mapping module maps words and characteristics to a high-dimension space. A principal component analysis module conducts principal component analysis in each corresponding word space, to obtain a projection matrix. A VLAD computation module computes a VLAD image representation vector; a second mapping module maps the VLAD image representation vector to the high-dimension space. A projection transformation module conducts projection transformation on the VLAD image representation vector obtained by means of projection. A normalization processing module conducts normalization on characteristics obtained by means of projection transformation, to obtain a final image representation vector. An obtained image representation vector is projected to a high-dimension space first, then projection transformation is conducted on a projection matrix computed in advance and vectors corresponding to words, to obtain a low-dimension vector; and in this way, the vectors corresponding to the words are consistent. The disclosed method and the processing device can obtain better robustness and higher performance.

Accelerating object detection techniques are described. In one or more implementations, adaptive sampling techniques are used to extract features from an image. Coarse features are extracted from the image and used to generate an object probability map. Then, dense features are extracted from high-probability object regions of the image identified in the object probability map to enable detection of an object in the image. In one or more implementations, cascade object detection techniques are used to detect an object in an image. In a first stage, exemplars in a first subset of exemplars are applied to features extracted from the multiple regions of the image to detect object candidate regions. Then, in one or more validation stages, the object candidate regions are validated by applying exemplars from the first subset of exemplars and one or more additional subsets of exemplars.