In this paper, an image approximation method is proposed. The method approximates the given image by preserving image's average color and color contrast. The experimental results show that the proposed method usually yields satisfactory results.
Shape-specific points are special data points invariant to translation, scaling, and rotation. The radius weighted mean (RWM) and the system center are two examples of shape-specific points. These points feature in contour registration, color quantization, and the detection of rotationally symmetric shape orientations. This study uses shape-specific points… (More)
In this manuscript, we propose a system which can automatically recognize the oyster racks in an aerial image. As the oyster racks are recognized, the volume of the oysters could thus be estimated and the price can be predicted in advance. Besides that, when a disaster such as a typhoon strikes on the offshore, the loss could also be estimated when the… (More)
In this manuscript, a system which automatically detects roads in the aerial image is proposed. The proposed method detects parallel lines in the image and calculates their centers as road centers. By examining color, width, and size-to-length ratio of detected road centers, the proposed method corrects some mislabeled objects. Besides that, the proposed… (More)
In this paper, a fast backlight module luminance inspection method is proposed. The proposed method inspects various backlight modules at once and all check points within the backlight modules are examined. Comparing to the traditional method which inspects one check point at a time, the proposed method is fast. The experimental results show that the… (More)
In this paper, a feature-preserving interpolative vector quantization method is proposed to compress images. The proposed method preserves the average color and color contrast on generating the approximation image and preserves mean, variance, and average radius on quantizing the residual image which is generated by subtracting the approximation image from… (More)