Altek Semiconductor Corp.

Altek Corporation

Altek Semiconductors Corporation

Wen-Yan Chang

Hong-Long Chou

Tai-Chang Yang

Yu-Chih Wang

Yi-Hong Tseng

Tsan-Wei Wang

Che-Lun Chuang

Chia-Chun Tseng

Hsin-Te Wang

Yin-Pin Chang

Chia-Chun Hsieh

Yun-Chin Li

Yu-Chen Huang

Kai-Yu Tseng

Shih-Yuan Peng

Yao-Sheng Wang

Shan-Lung Chao

Chung-Chia Kang

Su Ian Alias Eugene Lei

Yu-Chia Chung

Yun-Chin Lee

Yi-Yi Yu

Kaiyu Tseng

Shuo-Tse Hung

An image detection device and an image detection method are provided. The image detection method includes: obtaining an image, where the image includes an object; adjusting a first size of the image to generate an adjusted image; generating a first divided image and a second divided image according to the image; and detecting the object in the image based on a plurality of input images, where the plurality of input images includes the first divided image, the second divided image, and the adjusted image.

Image detection device and image detection method

An object detection device and an object detection method based on a neural network are provided. The object detection method includes: receiving an input image and identifying an object in the input image according to an improved YOLO-V2 neural network. The improved YOLO-V2 neural network includes a residual block, a third convolution layer, and a fourth convolution layer. A first input of the residual block is connected to a first convolution layer of the improved YOLO-V2 neural network, and an output of the residual block is connected to a second convolution layer of the improved YOLO-V2 neural network. Here, the residual block is configured to transmit, to the second convolution layer, a summation result corresponding to the first convolution layer. The third convolution layer and the fourth convolution layer are generated by decomposing a convolution layer of an original YOLO-V2 neural network.

Object detection device and object detection method based on neural network

A multi-camera electronic device and a control method thereof are proposed. The method includes the following steps. At least one camera of the electronic device is used for scene detection to generate photographing analysis information. All the photographing analysis information is collected, and joint photographing information including a joint target is generated through a communication process among all the cameras. An individual photographing parameter of each camera is generated according to the joint photographing information. Each camera is controlled to capture an image of the scene by using its individual photographing parameter to respectively generate a corresponding output image.

Multi-camera electronic device and control method thereof

An image capture device and a calibration method of phase detection autofocus thereof are provided. A contrast-based autofocus procedure is executed to move a lens to multiple lens positions, and a statistical distribution of focus values is obtained based on the contrast-based autofocus procedure. Whether the phase linear relationship for a phase detection autofocus procedure is calibrated is determined according to the statistical distribution of the focus values. If yes, then a first phase difference detected when the lens is located at one of the lens positions is obtained, and a second phase difference detected when the lens is located at another one of the lens positions is obtained. The phase linear relationship of the phase detection autofocus procedure is calibrated according to the one of the lens positions, the first phase difference, the other one of the lens positions, and the second phase difference.

Image capturing device and calibration method of phase detection autofocus thereof

An optimization method of image depth information and an image processing apparatus are provided. A to-be-repaired depth map generated based on a left image and a right image is obtained. A superpixel segmenting process is performed on the left image or the right image to obtain multiple superpixels. A plurality of image segments are obtained by aggregating the superpixels according to pixel information in the superpixels. A hole filling process is performed on holes of the to-be-repaired depth map to obtain a hole-filled depth map. A statistical analysis is performed on first valid depth values of the to-be-repaired depth map and second valid depth values of the hole-filled depth map to obtain a plurality of optimized depth values by using the ranges of the image segments, the ranges of the superpixels, the to-be-repaired depth map, and the hole-filled depth map.

Optimization method of image depth information and image processing apparatus

Method and apparatus for optimizing depth information are provided. One of a left image and a right image is divided into a plurality of segmentations for obtaining a plurality of segmentation maps. A necessary repair depth map is obtained, and the necessary repair depth map is partitioned into a plurality of depth planes according to a plurality of primary depth values and a camera parameter. The primary depth values are recorded in the necessary repair depth map having a plurality of holes. A plurality of optimized depth values are respectively generated for the holes in each of the depth planes by using the segmentation maps, and the optimized depth values are filled into the depth planes to obtain an optimized depth map.

Method and apparatus for optimizing depth information

An image capture device, a depth generating device and a method thereof are disclosed. The present disclosure is characterized in that a depth calculation technology with a structure light projection and a pictorial depth calculation technology are combined to better both of resolution and accuracy of the calculated image depth. In addition, the utilization of a modified flashlight enables the combination of the two technologies to be applied to a hand-held capture device.

Image capture device, depth generating device and method thereof

An image processing system and a method for object-tracing are provided. The method includes: receiving a first wide field of view image and a first narrow field of view image, and determining a to-be-traced object therefrom and choosing one image therefrom for serving as a first output image; using an area size of the to-be-traced object in the first output image as a reference area; comparing the reference area with the area sizes of the to-be-traced object from a second wide field of view image and a second narrow field of view image respectively so as to determine one of that as a main image, and respectively zooming and deforming the main image and an area corresponding to the other image, and then fusing a zoomed and deformed second image as a second output image.

Image processing system and method for object-tracing

An image capturing device and a method for generating a bokeh effect are provided. The method includes the following steps. An image including a current input pixel is captured. Next, blurring processes are performed on the image by using a first image blur filter and a second image blur filter so as to generate a plurality of first blur images and second blur images corresponding to different blur levels. A distance between the current input pixel and a focal plane is calculated to obtain a current distance. A first current blur image and a second current blur image are respectively selected from the first blur images and the second blur images according to the current distance. Next, a first current blur pixel of the first current blur image and a second current blur pixel of the second current blur image are combined to generate a current output pixel.

Method for generating image bokeh effect and image capturing device

The present invention discloses a method of capturing images and an image capturing device using the method. The image capturing device has a first lens module and a second lens module having a view angle which is smaller than that of the first lens module. The method comprises: increasing an exposure time and reducing a light sensitivity value of the first lens module and capturing a first image by using the first lens module; reducing the exposure time and increasing the light sensitivity value of the first lens module and capturing a second image by using the second lens module; extracting a plurality of image features from the first image and the second image respectively and determining a region corresponding to the second image in the first image; and merging the second image into the region in the first image to generate an output image.

Method of capturing images and image capturing device using the method

An image capturing device and a digital zooming method thereof are proposed in the invention. The method includes the following steps. A scene is captured by a primary lens and a secondary lens to generate a primary image and a secondary image. Image rectification is then performed on the primary and the secondary images to obtain two corresponding rectified images. Feature points detected and matched from the two rectified images are used to determine a corresponding overlapping region, respectively. Pixel displacement and depth map in the two overlapping regions could be calculated and estimated. Image zooming and warping techniques are performed on the two rectified images to obtain corresponding warped images using a recalculated homography matrix according to each specific zooming factor. Finally, the two overlapping regions in the warped image are fused by a weighted blending approach to generate a digital zoomed image.

Image capturing device and digital zooming method thereof

An image capturing device and a digital zoom display method are provided. The device includes two lens modules configured to respectively capture a first image and a second image, and their capturing view fields are substantially identical, a preview processing unit configured to generate a third image by down-sampling the first image according to a display unit's resolution, a feature extraction unit, an image zooming and distortion unit and an image fusing unit. The second image is trimmed for generating a fourth image according to the same size of the third image. A pixel offset feature corresponding with the third and fourth images is generated by the feature extraction unit. The image zooming and distortion unit generates a fifth image and a sixth image according to the pixel offset feature and zoom ratio to the image fusing unit to generate a combined image displayed on the display unit.

Image capturing device and digital zoom display method

The present disclosure illustrates a lens distortion correction method to solve influence for distortion correction caused by an alignment error between a lens center and a center of image sensor unit during assembling. The present disclosure is characterized in that the spatial geometric calibration is incorporated with the lens distortion correction and different image centers are selected repeatedly when transformation relationship of image coordinates is used to perform the lens distortion correction, so as to correct the image center of the image to be corrected and enhance the accuracy of lens distortion correction.

Lens distortion correction method

The present disclosure illustrates a camera array correction method. The method comprises steps of calculating the gain values between the images captured by cameras with the pre-measured characteristic of each of the cameras. By such correction method, the different cameras in the camera array can capture images of the same brightness values and color values simultaneously. In addition, the huge computation requirement due to the increasing of the cameras can be reduced effectively.

Camera array correction method

An image transfer apparatus and a method thereof comprise: capturing at least one first image, wherein the first image includes at least one face image; performing a face detection to obtain at least one face feature; a database has at least one identification information which comprises at least one face photo and a corresponding communication information; comparing the face feature with the face photo saved in the database; retrieving the corresponding communication information and the identification information corresponding to the face photo, if the face feature matches the face photo; performing the face image processing corresponding to the identification information in the first image, so as to obtain at least one second image; transmitting each second image according to the communication information of the processed face image in the second image.

Growing community of inventors

Miaoli County, Taiwan

Wen-Yan Chang