Industrial Technology Research Institute

Transpacific IP Limited

Cheng-Chin Chiang

Jun-Wei Hsieh

Tse Cheng

Chun-Wei Hsieh

Yea-Shuan Huang

Der-Lor Way

Shu-Cheng Huang

Shiaw-Shian Yu

Yao-Hong Tsai

A method and system of merging a pair of images to form a seamless panoramic image including the following steps. A set of feature points are extracted along the edges of the images, each feature point defining an edge orientation. A set of registration parameters is obtained by determining an initial set of feature points from a first one of the images which matches a set of feature points of a second one of the images. A seamless panoramic image is rendered using the first and second images with the set of registration parameters.

Apparatus and method for providing panoramic images

The present invention relates to methods and systems for an illuminant compensation. In particular, these methods and systems include a method for operations on an image, for example, an image of a human face. In the described methods and systems, it is determined for each pixel in the image whether it is part of the face region. A surface fitting is then determined based on only the pixels that are determined to be part of the face region. Also, described are methods and systems for image normalization wherein the standard deviation and average for the gray levels of the pixels are determined and then used to normalize the image so that the gray level for each of the pixels falls between a particular range.

Methods and system for illuminant-compensation

An apparatus and method of content-based image retrieval generate a plurality of training images, including a first part and a second part. Each training image of the first part is labeled as one of a positive bag or a negative bag. The training image is labeled a positive bag if the training image has a desirable character and labeled a negative bag if the training image does not have a desirable character. A set of N1 training images is identified from a set of all training images of the second part, which identified images have a feature most closely matching a first feature instance of a training image labeled as a positive bag. A first value corresponding to the first feature instance is calculated, based on the number of images labeled as positive bags that are identified in the set of N1 training images.

Method and apparatus for content-based image retrieval with learning function

A method is described for producing smooth transitions between a source vista and a destination vista with unknown camera axes in panoramic image based virtual environments. The epipoles on the source vista and the destination vista are determined to align the vistas. Corresponding control lines are selected in the vistas to compute the image flow between the vistas and to densely match the pixels. In-between image frames are computed by forward-resampling the source vista and backward-resampling the destination vista.

Producing transitions between vistas

A method and apparatus for displaying a selected portion of a panoramic image onto a view plane is provided. The method provides an environment map in the form of a plurality of pixel values representative of the panoramic image. A first portion of the pixel values representative of a selected first area of the panoramic image is mapped to a projection buffer. A second portion of the first portion of pixel values, representative of a desired area of the panoramic image to be viewed is mapped to the view plane. The view plane is displayed on the display.

Real-time player for panoramic imaged-based virtual worlds

A pair of images are stitched together by warping the pair of images into an environment map representative of a panoramic image. A first edge and a corresponding second edge for each of the first and second images, respectively, are detected. A set of edge position coordinates along the edge of the first warped image is determined. A set of possible matched solutions from the edge position coordinates of the first and second edge are generated. An optimum matched offset from the set of possible matched solutions is determined. Because the set of possible matched solutions is small and compact, the optimum matched offset can be determined efficiently from the set of solutions.

Intelligent stitcher for panoramic image-based virtual worlds

A character recognition device and system:

Growing community of inventors

Hsinchu, Taiwan

Cheng-Chin Chiang