Novel tools and techniques are provided for implementing digital microscopy imaging using deep learning-based segmentation and/or implementing instance segmentation based on partial annotations. In various embodiments, a computing system might receive first and second images, the first image comprising a field of view of a biological sample, while the second image comprises labeling of objects of interest in the biological sample. The computing system might encode, using an encoder, the second image to generate third and fourth encoded images (different from each other) that comprise proximity scores or maps. The computing system might train an AI system to predict objects of interest based at least in part on the third and fourth encoded images. The computing system might generate (using regression) and decode (using a decoder) two or more images based on a new image of a biological sample to predict labeling of objects in the new image.

Presented are intelligent vehicle systems for off-road driving incident prediction and assistance, methods for making/operating such systems, and vehicles networking with such systems. A method for operating a motor vehicle includes a system controller receiving geolocation data indicating the vehicle is in or entering off-road terrain. Responsive to the vehicle geolocation data, the controller receives, from vehicle-mounted cameras, camera-generated images each containing the vehicle's drive wheel(s) and/or the off-road terrain's surface. The controller receives, from a controller area network bus, vehicle operating characteristics data and vehicle dynamics data for the motor vehicle. The camera data, vehicle operating characteristics data, and vehicle dynamics data is processed via a convolutional neural network backbone to predict occurrence of a driving incident on the off-road terrain within a prediction time horizon. The system controller commands a resident vehicle system to execute a control operation responsive to the predicted occurrence of the driving incident.

Systems and methods for determining a dominant color in a digital image are provided and include dividing pixels of the digital image into pixel groups, with pixels in a first pixel group being closer to a center of the digital image than pixels in a second pixel group. Pixels in the first and second pixel groups having a chroma value greater than a predetermined chroma value threshold and a lightness greater than a low brightness threshold and less than a high brightness threshold are analyzed using a first sample rate for the first pixel group and a second sample rate for the second group. The first sample rate is greater than the second sample rate. A dominant color for the digital image is determined based on the analyzed pixels in the first and second pixel groups.

An example embodiment includes: a determination unit that, based on an image including an eye of a recognition subject, determines whether or not a colored contact lens is worn; and a matching unit that, when it is determined by the determination unit that the colored contact lens is worn, performs matching of the iris by using a feature amount extracted from a region excluding a predetermined range including an outer circumference of the iris out of a region of the iris included in the image.

Method for decomposing a complexly shaped object in a data set, such as a geobody (31) in a seismic data volume, into component objects more representative of the true connectivity state of the system represented by the data set. The geobody is decomposed using a basis set of eigenvectors (33) of a connectivity matrix (32) describing the state of connectivity between voxels in the geobody. Lineal subspaces of the geobody in eigenvector space are associated with likely component objects (34), either by a human interpreter (342) cross plotting (341) two or more eigenvectors, or in an automated manner in which a computer algorithm (344) detects the lineal sub-spaces and the clusters within them.

A system and process for extracting information from filled form images is described. In one example, the claimed invention first extracts textual information and the hierarchy in a blank form. This information is then used to extract and understand the content of filled forms. In this way, the system does not have to analyze from the beginning each filled form. The system is designed so that it remains as generic as possible. The number of hard-coded rules in the whole pipeline was minimized to offer an adaptive solution able to address the largest number of forms, with various structures and typography. The system is also created to be integrated as a built-in function in a larger pipeline. The form understanding pipeline could be the starting point of any advanced Natural Language Processing application.

A handwritten text processing system processes a digitized document including handwritten text input to generate an output version of the digitized document that allows users to execute text processing functions on the textual content of the digitized document. Each word of the digitized data is extracted by converting the digitized document into images, binarizing the images, and segmenting the images into binary image patches. Each binary image patch is further processed to identify if the word is machine-generated or if the word is handwritten. The output version is generated by combining underlying images of the pages of the digitized document with words from the pages superimposed in a transparent font at positions that coincide with the positions of the words in the underlying images.

In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersection contention areas in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute outputs—such as signed distance functions—that may correspond to locations of boundaries delineating intersection contention areas. The signed distance functions may be decoded and/or post-processed to determine instance segmentation masks representing locations and classifications of intersection areas or regions. The locations of the intersections areas or regions may be generated in image-space and converted to world-space coordinates to aid an autonomous or semi-autonomous vehicle in navigating intersections according to rules of the road, traffic priority considerations, and/or the like.

According to one example for segmenting image data, image data comprising color pixel data, IR data, and depth data is received from a sensor. The image data is segmented into a first list of objects based on at least one computed feature of the image data. At least one object type is determined for at least one object in the first list of objects. The segmentation of the first list of objects is refined into a second list of objects based on the at least one object type. In an example, the second list of objects is output.

Identifying objects in images is a difficult problem, particularly in cases an original image is noisy or has areas narrow in color or grayscale gradient. A technique employing a convolutional network has been identified to identify objects in such images in an automated and rapid manner. One example embodiment trains a convolutional network including multiple layers of filters. The filters are trained by learning and are arranged in successive layers and produce images having at least a same resolution as an original image. The filters are trained as a function of the original image or a desired image labeling; the image labels of objects identified in the original image are reported and may be used for segmentation. The technique can be applied to images of neural circuitry or electron microscopy, for example. The same technique can also be applied to correction of photographs or videos.