National Cheng-Kung University

Hong Kong Applied Science and Technology Research Institute Company, Limited

Chun-Fu Chen

He-Yuan Lin

Gwo Giun (Chris) Lee

Gwo Giun Lee

Ming-Jiun Wang

Yan Huo

Chunhui Cui

Huan-Hsiang Lin

Ciao-Siang Siao

Jhen-Yue Hu

Cheng-Shiun Tsai

Jhu-Syuan Ho

Ping-Keng Jao

An electrocardiography signal extraction method is performed on a processor of a computer system and includes receiving an electrocardiography signal, performing a time-frequency transformation on the received electrocardiography signal to generate a corresponding scalogram, selecting a predetermined R-pertinent scale, performing the time-frequency transformation at the selected predetermined R-pertinent scale to generate a R-pertinent summarized response, obtaining a R peak position, selecting a predetermined QRS-pertinent scale, performing the time-frequency transformation at the selected predetermined QRS-pertinent scale, obtaining a Q peak position and a S peak position of the electrocardiography signal by finding relative maximum negative responses before and behind the R peak position respectively, obtaining a QRSon position and a QRSoff position by finding relative minimum second derivatives of the responses before the Q peak position and behind the S peak position, respectively.

Electrocardiography signal extraction method

A cell image segmentation method includes receiving a cell image, performing a nuclei initialization step to find an internal marker and an external marker to obtain a potential nuclei and a potential cell boundary, calculating a gradient map of the received cell image, performing a filtering step on the gradient map to generate a filtered gradient map, performing a nuclei detection step to obtain a segmented nuclei, and performing a nuclei validation step to obtain a valid nuclei. The nuclei initialization step includes performing a blob detection step to obtain a nuclei candidate, an outlier removal step to obtain the internal marker, a distance transform step to obtain a distance map, and a cell boundary initialization step to obtain the external marker. In another embodiment, a nuclear-to-cytoplasmic ratio evaluation method using the above cell image segmentation method is proposed.

Cell image segmentation method and a nuclear-to-cytoplasmic ratio evaluation method using the same

This invention discloses a method for object tracking, including determination of an area scaling ratio of the object in a video image sequence. In one embodiment, a centroid of the object is determined. One or more directed straight lines are selected, each passing through the centroid, extending from an end of the object's boundary to an opposite end thereof, and having a direction that is upward. A length scaling ratio for each directed straight line is determined by: determining a motion vector for each selected pixel on the line; computing a scalar component of the motion vector projected onto the line; estimating a change of the line's length according to the scalar components obtained for all pixels; and determining the length scaling ratio according to the change of the line's length. The area scaling ratio is computed based on the length scaling ratios for all directed straight lines.

Scale changing detection and scaling ratio determination by using motion information

A method for depth map generation is disclosed, capable of generating a depth map corresponding an image signal, for the application of a 2D to 3D image transformation system. In the depth map generated by the disclosed method, each of the plural image regions of the image signal is assigned with a depth value. Besides, by means of comparing the depth map with another depth map of the earlier time point, the disclosed method can generate a modulated depth map, for assigning a depth value to each of the plural image regions of the image signal more precisely. Thus, the transformation performance and efficiency of the 2D to 3D image transformation system are hereby improved.

Method for depth map generation

The present invention relates to a method for merging regions in the image/video, capable of merging plural of image regions into an image merging region. In the disclosed method, these image regions are first sequenced basing on their compactness value. Then, one of these image regions is designated as a reference image region, and a merging test process is executed by merging the reference image region with one of the nearby image regions thereof in sequence, for forming a temporal image merging region. Later, the compactness value of the temporal image merging region is compared with the compactness value of the two consisting image regions thereof, respectively. When the compactness value of the temporal image merging region is larger than either one of the compactness value of the two consisting image regions thereof, the temporal image merging region is designated as an image merging region.

Method for merging the regions in the image/video

A method for color feature extraction extracts a color feature vector representative of the color of each image pixel contained in an image signal. The method comprises: receiving the image signal; mapping the image signal to a color space model, where the color of each of the plural image pixels is represented by a first parameter, a second parameter, and a third parameter; obtaining an adjusted second parameter; clustering the plural image pixels into plural color regions or plural fuzzy regions of a color plane of the color space model; and designating the color feature vector to each of the plural image pixels based on the clustering result.

Method for color feature extraction

A method for image/video segmentation, capable of segmenting an image signal for obtaining plural texture color feature regions, by utilizing both of the advantages carried by the texture feature and the color feature is disclosed. The method comprises the following steps: (A) receiving an image signal including plural image pixels; (B) executing a Gabor filtering process and a value operation process on each of the plural image pixels; (C) designating each of the plural image pixels a corresponding texture feature vector basing on the result of the value operation process; (D) executing a segmentation process on the image signal basing on the texture feature vector of each of the plural image pixels, for obtaining plural texture feature regions; and (E) executing a re-segmentation process on plural color feature regions basing on the distribution of the plural texture feature regions, for obtaining plural texture color feature regions.

Growing community of inventors

Tainan, Taiwan

Chun-Fu Chen