Abstract: According to one embodiment, an image processing device includes a hardware processor implemented by one or more processors. The hardware processor acquires a first image of a first object and a second image of a second object which is different from the first object, the images captured by an image capture processing device including an image capturing element and an optical system which images an object image on an image capturing surface of the image capturing element. The hardware processor measures a point spread function of the optical system based on the first image and the second image.

Abstract: According to an embodiment, a reading system includes a first extractor and a reader. The first extractor extracts, from an image in which a meter is imaged, a first region surrounded with a first contour, and a second region surrounded with a second contour positioned outward of the first contour. The reader calculates a first indication based on the first region, calculates a second indication based on the second region, calculates a first score relating to the first indication based on the first region, and calculates a second score relating to the second indication based on the second region.

Abstract: In one example embodiment, a computer-implemented method includes obtaining sensor data from a sensor, the sensor data corresponding to an image frame, and the sensor data including a first portion that corresponds to a portion of the image frame. The method includes pipelining the first portion of the sensor data into a machine-learned model before the sensor data corresponding to the entire image frame is transferred from the sensor to a memory device, to perform one or more inference operations on the first portion of the sensor data. The method includes generating as an output of the machine-learned model, in response to pipelining the sensor data corresponding to each portion of the image frame into the machine-learned model, a detection or classification of the one or more objects indicated within the sensor data.

Abstract: An information processing apparatus includes: a memory; and a processor coupled to the memory and configured to: calculate a positional difference and a degree of similarity in feature value between each feature point in a verification image captured by an imaging device and each of a plurality of feature points in a registered image registered in advance; and match the verification image against the registered image by using the degree of similarity to a feature point having the degree of similarity that is second highest or lower for each feature point in the registered image in a case where a positional difference from a feature point having the degree of similarity that is highest in the verification image is greater than a threshold value.

Abstract: An image processing method acquires an image, restores a saturated region in which a pixel in the image has a first reference value based on a first illuminance component of the image, enhances a dark region in which a value of a pixel in the image is less than a second reference value based on the restored saturated region and the first illuminance component, and outputs a dark region-enhanced image.

Abstract: An apparatus including a first memory area and a second memory area is provided with a control method including specifying one or a plurality of types of image processing to be applied in the first memory area, specifying a size of obtainment target image data as a predetermined size based on a memory capacity of the second memory area and a content of the specified one or plurality of types of image processing; and obtaining first divided image data having the specified predetermined size in predetermined image data.

Abstract: An information processing device and method for sharing of compressed training data for neural network training is provided. The information processing device receives a first image which includes an object of interest. The information processing device extracts, from the received first image, a region of interest which includes the object of interest. Once extracted, the extracted region of interest is provided to an input layer of N numbers of layers of a first neural network, trained on an object detection task. The information processing device selects an intermediate layer of the first neural network and extracts a first intermediate result as an output generated by the selected intermediate layer of the first neural network based on the input RoI. Once extracted, the information processing device shares the extracted first intermediate result as compressed training data with a server to train a second neural network on the object detection task.

Abstract: The method is for dividing dark objects, sub-structures and background of an image from an electron microscope into segments by analyzing pixel values. The segments are transformed and aligned so that the transformed objects, sub-structures and background are meaningfully comparable. The transformed segments are clustered into classes which are used for ontological investigation of samples that are visualized by using electron microscopy. A triangle inequality comparison can be used to further cluster groups of objects to transfer understanding from different interactions between objects and to associate interactions with each other.

Abstract: A system and process to determine whether a digital image has been manipulated involves determining expected locations of non-standard pixels in the digital image, and determining a feature for evaluating the non-standard pixels. The feature in pixels of the digital image that are located at the expected locations of non-standard pixels is then measured, and a statistical measure of the feature of pixels in the digital image that are located at the expected locations of non-standard pixels is evaluated. The digital image is assessed to determine a probability that the digital image includes a manipulated portion, based on the statistical measure. The system and process can also determine a make and model of an image sensing device via an examination of the non-standard pixels.

Abstract: A system for providing information about an environment to a user within the environment is featured. An electronic processor is configured to receive input including a user selection of an object of interest from among potential objects of interest. The electronic processor is further configured to provide output to guide the user to move the detection apparatus to position the object of interest near a reference point on a field of view of the detection apparatus, obtain multiple images of the object of interest during the user's movement of the detection apparatus, and crop each of the images to keep the object of interest near a reference point on each of the images.

Abstract: An image processing apparatus included in a vehicle comprises: a division section that is configured to divide into a plurality of areas, a captured image sequentially captured by an imaging device that captures images around the vehicle; an importance set section that is configured to set an importance level for each of the areas; and a compression section that is configured to compress the captured image for each of the areas.

Abstract: In an approach for propagating labels of objects in an image, a processor receives the image. A processor performs a normalization of the image. A processor runs the image through a pre-trained object detector. A processor receives a set of detected objects from the pre-trained object detector. A processor determines a width dimension and a height dimension of a bounding box for each detected object of the set of detected objects. A processor propagates a label for each instance of each detected object in the image with the respective bounding box using prior geometric knowledge of bounding box placement. A processor inverses the normalization of the labeled image. A processor outputs the labeled image.

Abstract: The present disclosure provides a gesture recognition method. The method includes the following steps: acquiring a depth image of a user; determining a point set of a two-dimensional image indicating a palm based on a depth information of the depth image; and, determining a gesture based on the point set.

Abstract: A method and an apparatus for generating vehicle damage information are provided. The method includes: acquiring a damage area image of a target vehicle; performing image segmentation on the damage area image to obtain a first suspected damage area; inputting the damage area image to a pre-trained detection model to obtain a second suspected damage area, the detection model being configured to detect a location of the suspected damage area in the image; determining a damage image feature based on the first suspected damage area and the second suspected damage area; and inputting the damage image feature to a pre-trained classification model to generate a damage type, the classification model being configured to characterize a corresponding relationship between the image feature and the damage type.

Abstract: The present disclosure describes methods, devices, and storage medium for recognizing a target object in a target image. The method including obtaining, by a device, an image recognition instruction, the image recognition instruction carrying object identification information used for indicating a target object in a target image. The device includes a memory storing instructions and a processor in communication with the memory. The method includes obtaining, by the device, an instruction feature vector matching the image recognition instruction; obtaining, by the device, an image feature vector set matching the target image, the image feature vector set comprising an ith image feature vector for indicating an image feature of the target image in an ith scale, and i being a positive integer; and recognizing, by the device, the target object from the target image according to the instruction feature vector and the image feature vector set.

Abstract: Techniques for the modification of at least part of a target image (e.g., scene objects within the target image), e.g., to make the target image appear that it was captured at a different time (e.g., a different time of day, different time of year) are disclosed. This “dynamic re-timing” of the target image may be achieved by finding one or more source images including the same (or similar) scene depicted in the target image (but, e.g., captured at different times), extracting stylistic elements from the source image(s), and then modifying at least part of the target image in a realistic fashion (e.g., not altering the geometry of objects in the target image), based on one or more extracted stylistic elements from the source image(s). Three-dimensional modeling of scene objects may allow a more realistic-looking transfer of the extracted stylistic elements onto scene objects in the target image to be achieved.

Abstract: The present disclosure provides a dynamic tone mapping method, a mobile terminal, and a computer readable storage medium. The method includes: acquiring maximum brightness information and average brightness information of a frame to be displayed on the display terminal; inquiring a tone mapping data group respectively corresponding to the maximum brightness information and the average brightness information in a preset tone mapping look-up table; and calling the tone mapping data group and transforming a tone mapping on the frame to be displayed on the display terminal. The present disclosure can change the tone mapping data group for transforming the tone mapping in real time according to the maximum brightness information and the average brightness information of the frame monitored in real time, to reasonably utilize the hardware dynamic range and present a better HDR effect.

Abstract: A method of deblurring an observed image acquired by an image sensor in order to determine an observable image corresponding to the deblurred observed image. The observable image and the observed image each are formed by a set of pixels defined by at least one numerical value. The method involves expressing the observable image as a solution minimizing a Tikhonov functional defined by the observed image, applying a spreading function at the point of the image sensor and applying a wavelet transform operator. The Tikhonov functional is expressed as a sum of at least two terms. The method further involves determining the observable image by implementing an iterative projection algorithm released on a closed convex, at each iteration of which, the successive application of a projection operator associated with each of the terms of the Tikhonov functional.

Abstract: System, methods, and other embodiments described herein relate to training a depth model for monocular depth estimation. In one embodiment, a method includes generating, as part of training the depth model according to a supervised training stage, a depth map from a first image of a pair of training images using the depth model. The pair of training images are separate frames depicting a scene from a monocular video. The method includes generating a transformation from the first image and a second image of the pair using a pose model. The method includes computing a supervised loss based, at least in part, on reprojecting the depth map and training depth data onto an image space of the second image according to at least the transformation. The method includes updating the depth model and the pose model according to at least the supervised loss.

Abstract: Point clouds of objects are compared and matched using logical arrays based on the point clouds. The point clouds are azimuth aligned and translation aligned. The point clouds are converted into logical arrays for ease of processing. Then the logical arrays are compared (e.g. using the AND function and counting matches between the two logical arrays). The comparison is done at various quantization levels to determine which quantization level is likely to give the best object comparison result. Then the object comparison is made. More than two objects may be compared and the best match found.