A gas-detection image processing device includes first, second, and third processors. The first processor generates a plurality of first images by applying processing to extract a gas candidate region to each of a plurality of infrared images captured in time series during a predetermined period. The second processor generates a second image, while using the first images, by applying processing to extract an appearance region indicating that a gas candidate region has appeared in at least a part of the predetermined period. The second processor generates two or more second images by applying the processing to extract the appearance region to the first images generated in a manner corresponding to two or more of the predetermined periods respectively. The third processor generates a third image by applying processing to extract a common region of the appearance regions while using the two or more of the second images.

Method, an electronic device and a storage medium for living body detection based on face recognition are disclosed. The method comprises: obtaining to-be-detected infrared image and visible light image; performing edge detection and texture feature extraction on the infrared image, and feature extraction on the visible light image through a convolutional neural network; and determining whether the infrared and visible light images pass living body detection based on results of the edge detection and texture feature extraction on the to-be-detected infrared image, and a result of feature extraction on the to-be-detected visible light image through the convolutional neural network. The method, an electronic device and a storage medium for living body detection based on face recognition combine the advantages of three technologies of edge detection, texture feature extraction and convolution neural network, effectively perform living body detection, and improve the determination accuracy.

Method, an electronic device and a storage medium for living body detection based on face recognition are disclosed. The method comprises: obtaining to-be-detected infrared image and visible light image; performing edge detection and texture feature extraction on the infrared image, and feature extraction on the visible light image through a convolutional neural network; and determining whether the infrared and visible light images pass living body detection based on results of the edge detection and texture feature extraction on the to-be-detected infrared image, and a result of feature extraction on the to-be-detected visible light image through the convolutional neural network. The method, an electronic device and a storage medium for living body detection based on face recognition combine the advantages of three technologies of edge detection, texture feature extraction and convolution neural network, effectively perform living body detection, and improve the determination accuracy.

An example method of infrared access, comprising, receiving a plurality of visual images, receiving a plurality of infrared images, calibrating the plurality of visual images to the plurality of infrared images, determining an average temperature of the plurality of infrared images, determining an outlier temperature of an outlier infrared image of the plurality of infrared images and matching the outlier infrared image to a visual image.

An object is to provide a filter learning device capable of optimizing recognition processing using features obtained from the characteristics of light. The filter learning device (10) according to the present disclosure includes an optical filter unit (11) for extracting a filter image from an image for learning by using a filter condition determined according to a filter parameter, a parameter updating unit (12) for updating the filter parameter with a result obtained by executing image analysis processing on the filter image, and a sensing unit (13) for sensing an input image by using a physical optical filter that satisfies a filter condition determined according to the updated filter parameter.

An image sensor includes a first sensor pixel and a second sensor pixel that vertically overlap each other. The first sensor pixel includes a first signal generation circuit, and a first photoelectric converter that is connected to the first signal generation circuit and configured to generate first information from light having a first wavelength. The second sensor pixel includes a second signal generation circuit, and a second photoelectric converter that is connected to the second signal generation circuit and configured to generate second information from light having a second wavelength. A first horizontal surface area of the first photoelectric converter is different from a second horizontal surface area of the second photoelectric converter. An image sensor module includes the image sensor, a light source configured to emit light to a target object, and a dual band pass filter configured to selectively pass light reflected from the target object.

An optical fingerprint sensor and an electronic device having same are provided. The optical fingerprint sensor includes a light-sensing element, an optical filter layer and an optical lens. The light-sensing element includes: a light-sensing base layer having a groove in a side surface thereof; a first light-sensing layer configured to receive visible light and arranged in the groove; and a second light-sensing layer configured to receive invisible light, and arranged between an inner wall surface of the groove and an outer wall surface of the first light-sensing layer. The optical filter layer is stacked on a side of the light-sensing element where the groove is formed. The optical lens is configured for focusing and stacked on a side of the optical filter layer facing away from the light-sensing element.

An image processing apparatus includes an acquisition unit that acquires a hologram obtained by imaging a plurality of granules contained within an imaging visual field, a generation unit that generates, from the hologram, phase difference images at positions different from each other in an optical axis direction in a case in which the hologram is captured, a specifying unit that specifies a plurality of image ranges in a direction of a plane intersecting the optical axis direction, which correspond to the plurality of granules, in an averaged image obtained by averaging at least some of the phase difference images, and an extraction unit that extracts the phase difference image at a center position of a corresponding granule in the optical axis direction for each of the plurality of image ranges.

An image adaptive feature extraction method includes dividing an image into a plurality of blocks, performing a feature extraction processing on the plurality of blocks, and obtaining a block feature from each of the plurality of blocks after the feature extraction processing; calculating each block feature by means of a support vector machine (SVM) classifier, wherein each block feature is calculated to obtain a hyperplane normal vector; setting a threshold value, determining the block feature according to the hyperplane normal vector, recording the block as an adaptive feature block when a value of the hyperplane normal vector is higher than the threshold value, and integrating each adaptive feature block to form an adaptive feature image. Because an image adaptive feature extraction process is performed before a pedestrian image detection is calculated, and effective feature data is then selected, computational efficiency is boosted and detection pedestrian error probability is reduced.

Embodiments for implementing intelligent boundary delineation of a region of interest of an organism in two spatial dimensions in a computing environment by a processor. Time series data of a contrast agent in one or more regions of interest captured from multispectral image streams may be collected. One or more regions of interest having one or more perfusion patterns may be identified from the time series data. Boundaries of the one or more regions of interest may be delineated into at least two spatial dimensions, wherein the boundaries of the one or more regions of interest include one or more selected labels.