The present disclosure provides a computer-implemented method of, and system for, characterizing the phenotype of a plant. The method includes: (i) obtaining mesh data representing a surface of the plant, said mesh data including data representing a plurality of polygons having respective sets of vertices, each vertex having a spatial coordinate; and (ii) applying at least two segmentations of progressively finer resolution to the mesh data to assign the vertices to distinct morphological regions of the plant.

A method and apparatus for segmenting an object from a three-dimensional image are disclosed. According to the method, first, a surface of the object is estimated using scale estimation processes such as Laplacian-of-Gaussian filters in one, two or three dimensions. Second, the estimated surface is transformed by having a shrink function applied to it independently in each dimension to give a regularly shaped (preferably substantially spherical), non-isotropic shape. The object is segmented from the volume around it, and is inverse-transformed to obtain the original shape, which shape is then isolated from the image volume.

The present invention provides a method for object segmentation in videos tagged with semantic labels, including: detecting each frame of a video sequence with an object bounding box detector from a given semantic category and an object contour detector, and obtaining a candidate object bounding box set and a candidate object contour set for each frame of the input video; building a joint assignment model for the candidate object bounding box set and the candidate object contour set and solving the model to obtain the initial object segment sequence; processing the initial object segment, to estimate a probability distribution of the object shapes; and optimizing the initial object segment sequence with a variant of graph cut algorithm that integrates the shape probability distribution, to obtain an optimal segment sequence.

A method for extracting a main subject of an image is disclosed. The method may include determining whether a region to be recognized corresponding to a specified feature exists in the image to be processed. The method may also include determining a main subject region containing the main subject of the image to be processed in accordance with a preset feature parameter of the main subject region and the coordinates and size of the region to be recognized when the region to be recognized exists. The method may further extracting an image of the main subject region as a foreground image for an extraction process of a foreground target, and taking the extracted image as the main subject of the image to be processed.

A method for identifying information in a document may include analyzing the document for a text block containing a structure element, wherein said structure element is a position, font attribute, or text character; applying a rule based analysis on the text block to identify an adjacent label and field containing a value; and identifying said label and said value as a label and value pair in the document.

An intelligent system detects triangles in digital photographic images, including portrait photography. The method extracts a set of filtered line segments as candidate triangle sides and/or objects as candidate triangle vertices. A modified RANSAC algorithm is utilized to fit triangles onto the set of line segments and/or vertices. Two metrics may then be used evaluate the fitted triangles. Those with high fitting scores are considered as detected triangles. The system can accurately locate preeminent triangles in photographs without any knowledge about the camera parameters or lens choices. The invention can also help amateurs gain a deeper understanding and inspirations from professional photographic works.

To improve efficiency of computing devices and improve the user experience thereon when searching for content items, the systems and methods disclosed herein provide content item and source detection. Non-textual input is converted to a searchable format and corresponding content items are searched for based on the searchable format.

An image processing apparatus including: a processor; and memory storing computer-readable instructions therein, the computer-readable instructions, when executed by the processor, causing the image processing apparatus to perform: acquiring target image data configured by a plurality of pixels and representing a target image including a character; acquiring a character code corresponding to the character in the target image; acquiring an index value relating to a number of a plurality of character pixels configuring the character in the target image by using the character code corresponding to the character in the target image; determining a first extraction condition by using the index value; and extracting the plurality of character pixels satisfying the first extraction condition from the plurality of pixels in the target image.

Examples of various method and systems are provided for information extraction from scene information. 2D image information can be generated from 2D images of the scene that are overlapping at least part of one or more object(s). The 2D image information can be combined with 3D information about the scene incorporating at least part of the object(s) to generate projective geometry information. Clustered 3D information associated with the object(s) can be generated by partitioning and grouping 3D data points present in the 3D information. The clustered 3D information can be used to provide, e.g., measurement information, dimensions, geometric information, and/or topological information about the object(s). Segmented 2D information can also be generated from the 2D image information. Validated 2D and 3D information can be produced by cross-referencing between the projective geometry information, clustered 3D information, and/or segmented 2D image information, and used to label the object(s) in the scene.

Disclosed is a system enabling the participation of a third-party computer program in a shopping activity between a vendor and consumer. The system is a software application that resides in part on a consumer smart device and in part on a publisher's system server. The present system enables the consumer smart device to transform a published advertising image from a hardcopy (magazine) page to a digital OCR fingerprint representative of the hardcopy page, and to sent the OCR fingerprint to the publisher's system server. The OCR fingerprint is compared against a database of other similarly generated OCR fingerprints of hardcopy pages from the magazine, including the advertising page of interest, for a match. Upon finding a suitable match, the vendor and item information for the items for sale on the advertising page are displayed on the smart device, enabling the consumer to browse the information and implement a purchase.