System and method for an active learning system including a sensor obtains data from a scene including a set of images having objects. A memory to store active learning data including an object detector trained for detecting objects in images. A processor in communication with the memory, is configured to detect a semantic class and a location of at least one object in an image selected from the set of images using the object detector to produce a detection metric as a combination of an uncertainty of the object detector about the semantic class of the object in the image (classification) and an uncertainty of the object detector about the location of the object in the image (localization). Using an output interface or a display type device, in communication with the processor, to display the image for human labeling when the detection metric is above a threshold.

Localization-aware active learning for object detection

An apparatus includes an object detector configured to receive image data of a scene viewed from the apparatus and including an object. The image data is associated with multiple scale space representations of the scene. The object detector is configured to detect the object responsive to location data and a first scale space representation of the multiple scale space representations.

Object detection using location data and scale space representations of image data

Techniques and systems are provided for processing image data using one or more neural networks For example, a patch of raw image data can be obtained The patch can include a subset of pixels of a frame of raw image data, and the frame can be captured using one or more image sensors The patch of raw image data includes a single color component for each pixel of the subset of pixels At least one neural network can be applied to the patch of raw image data to determine a plurality of color component values for one or more pixels of the subset of pixels A patch of output image data can then be generated based on application of the at least one neural network to the patch of raw image data The patch of output image data includes a subset of pixels of a frame of output image data, and also includes the plurality of color component values for one or more pixels of the subset of pixels of the frame of output image data Application of the at least one neural network causes the patch of output image data to include fewer pixels than the patch of raw image data Multiple patches from the frame can be processed by the at least one neural network in order to generate a final output image In some cases, the patches from the frame can be overlapping so that the final output image contains a complete picture

Image signal processor for processing images

An image processing device is provided that enables an operator to reduce time and effort, and that enables an image to be read stably without receiving the influence of a shadow generated after calibration. The image processing device includes: a tint component removing unit that removes a tint component from a captured image; a character information removing unit that removes character information from an image obtained by removing the tint component; a dividing unit that performs grouping on the captured image according to a combination of hue and saturation; a calculating unit that calculates, for each group, correction data for correcting the shadow in accordance with an image obtained by removing the character information and an image obtained by grouping; and a correcting unit that corrects the captured image in accordance with the calculated correction data.

Image processing device and image processing method

In a rectangular region detection mechanism, a to-be-processed image information is received, where the to-be-processed image information comprises at least two images, and where the at least two images comprise a same plurality of first feature points A plurality of first edge line segments in one of the at least two images are detected Four first edge line segments from the plurality of first edge line segments are determined Locations of photographed points corresponding to the plurality of first feature points in a region formed by the four first edge line segments are determined based on location information of the plurality of first feature points The region is determined as a rectangular region when the photographed points corresponding to the plurality of first feature points in the region are coplanar

Image Processing Method and Device

A method for cropping photos images captured by a user from an image of a page of a photo album is described. Corners in the page image are detected using corner detection algorithm or by detecting intersections of line-segments (and their extensions) in the image using edge, corner, or line detection techniques. Pairs of the detected corners are used to define all potential quads, which are then are qualified according to various criteria. A correlation matrix is generated for each potential pair of the qualified quads, and candidate quads are selected based on the Eigenvector of the correlation matrix. The content of the selected quads is checked using a salience map that may be based on a trained neuron network, and the resulting photos images are extracted as individual files for further handling or manipulation by the user.

Natalie Verter

Papers

System and method for detecting objects in an image