Seiko Epson Corporation

Jie Wang

Ivo Moravec

Syed Alimul Huda

Rastislav Lukac

Guoyi Fu

Yang Yang

Dibyendu Mukherjee

Mirza Tahir Ahmed

Susan Yang

A method includes: (A) receiving a selection of a 3D model stored in one or more memories, the 3D model corresponding to an object and (B) setting a camera parameter set for a camera for use in detecting a pose of the object in a real scene. The method also includes (C) generating at least one 2D synthetic image based at least on the camera parameter set by rendering the 3D model in a view range for generating training data.

Methods and systems for training an object detection algorithm using synthetic images

A non-transitory computer readable medium embodies instructions that cause one or more processors to perform a method. The method includes: (A) receiving a selection of a 3D model stored in one or more memories, the 3D model corresponding to an object, and (B) setting a camera parameter set for a camera for use in detecting a pose of the object in a real scene. The method also includes (C) receiving a selection of data representing a view range, (D) generating at least one 2D synthetic image based on the camera parameter set by rendering the 3D model in the view range, (E) generating training data using the at least one 2D synthetic image to train an object detection algorithm, and (F) storing the generated training data in one or more memories.

A non-transitory computer readable medium embodies instructions that cause one or more processors to perform a method. The method includes: (A) receiving, in one or more memories, a 3D model corresponding to an object, and (B) setting a depth sensor characteristic data set for a depth sensor for use in detecting a pose of the object in a real scene. The method also includes (C) generating blurred 2.5D representation data of the 3D model for at least one view around the 3D model based on the 3D model and the depth sensor characteristic data set, to generate, on the basis of the 2.5D representation data, training data for training an object detection algorithm, and (D) storing the training data in one or more memories.

Methods and systems for shape based training for an object detection algorithm

A head-mounted display device includes a camera, an inertial sensor in a first spatial relationship with the camera, and a processor that: acquires an image data sequence from the camera; and acquires a sensor data sequence from the inertial sensor; derives a first pose of an object based at least on one of image frames in the image data sequence and template data created based on a 3D model corresponding to the object; derives a second spatial relationship between an object coordinate system defined on the object or the 3D model and a global coordinate system based at least on the first pose or a pose tracked from the first pose, the sensor data sequence and the first spatial relationship; and derives a second pose of the object based at least on the image data sequence, the sensor data sequence and the second spatial relationship using a non-linear estimation algorithm.

Information processing device and computer program

Face verification is performed using video data. The two main modules are face image capturing and face verification. In face image capturing, good frontal face images are captured from input video data. A frontal face quality score discriminates between frontal and profile faces. In face verification, a local binary pattern histogram is selected as the facial feature descriptor for its high discriminative power and computational efficiency. Chi-Square (&#x3c7;) distance between LBP histograms from two face images are then calculated as a face dissimilarity measure. The decision whether or not two images belong to the same person is then made by comparing the corresponding distance with a pre-defined threshold. Given the fact that more than one face images can be captured per person from video data, several feature based and decision based aggregators are applied to combine pair-wise distances to further improve the verification performance.

System and method for face verification using video sequence

An input image (e.g. a digital RGB color image) is subjected to an eye classifier that is targeted at discriminating a complete eye pattern from any non-eye patterns. The red-eye candidate list with associated bounding boxes that are generated by the red-eye classifier are received. The bounding rectangles are subjected to object segmentation. A connected component labeling procedure is then applied to obtain one or more red regions. The largest red region is then chosen for feature extraction. A number of features are then extracted from this region. Then these features are used to determine if the particular candidate red-eye object is a mouth.

Mouth removal method for red-eye detection and correction

Automatic face recognition. In a first example embodiment, a method for automatic face recognition includes several acts. First, a face pattern and two eye patterns are detected. Then, the face pattern is normalized. Next, the normalized face pattern is transformed into a normalized face feature vector of Gabor feature representations. Then, a difference image vector is calculated. Next, the difference image vector is projected to a lower-dimensional intra-subject subspace extracted from a pre-collected training face database. Then, a square function is applied to each component of the projection. Next, a weighted summation of the squared projection is calculated. Then, the previous four acts are repeated for each normalized gallery image feature vector. Finally, the face pattern in the probe digital image is classified as belonging to the gallery image with the highest calculated weighted summation where the highest calculated weighted summation is above a predefined threshold.

Automatic face recognition

Automatic red-eye object classification in digital images using a boosting-based framework. In a first example embodiment, a method for classifying a candidate red-eye object in a digital photographic image includes several acts. First, a candidate red-eye object in a digital photographic image is selected. Next, a search scale set and a search region for the candidate red-eye object where an eye object may reside is determined. Then, the number of subwindows that satisfy an AdaBoost classifier is determined. This number is denoted as a vote. Next, the maximum size of the subwindows that satisfy the AdaBoost classifier is determined. Then, a normalized threshold is calculated by multiplying a predetermined constant threshold by the calculated maximum size. Next, the vote is compared with the normalized threshold. Finally, the candidate red-eye object is transformed into a true red-eye object if the vote is greater than the normalized threshold.

Growing community of inventors

Markham, Canada

Jie Wang