Abstract: An optical detecting device includes an image capturing device and a processor. The processor is coupled to a light source and an image capturing device. The processor is configured to adjust a light intensity of the light source for irradiating a correction object in order that a gray value of at least one image block, captured by the image capturing device, of the correction object matches a target correction value, and record a target light intensity while the target light intensity matches the target correction value; control the light source to irradiate light on a testing object with the target light intensity, and control the image capturing device to capture a testing object image of the testing object; and calculate ratios of a target gray value to the gray value of a plurality of pixels of the testing object image to obtain a mapping table.

Abstract: An image inspection method includes capturing a target object image, which the target object image comprises a plurality of graphical features; choosing a block image comprising a specific graphical feature of the plurality of graphical features from the target object image; capturing all the graphical features of the block image to obtain a region of interest (ROI); executing a filtering process or a recovering process on the ROI to obtain a pre-processed region; and inspecting, according to the pre-processed region, the target object image to determine whether the target object image has defects.

Abstract: An image inspection method includes capturing a target object image, which the target object image comprises a plurality of graphical features; choosing a block image comprising a specific graphical feature of the plurality of graphical features from the target object image; capturing all the graphical features of the block image to obtain a region of interest (ROI); executing a filtering process or a recovering process on the ROI to obtain a pre-processed region; and inspecting, according to the pre-processed region, the target object image to determine whether the target object image has defects.

Abstract: An optical detecting device includes an image capturing device and a processor. The processor is coupled to a light source and an image capturing device. The processor is configured to adjust a light intensity of the light source for irradiating a correction object in order that a gray value of at least one image block, captured by the image capturing device, of the correction object matches a target correction value, and record a target light intensity while the target light intensity matches the target correction value; control the light source to irradiate light on a testing object with the target light intensity, and control the image capturing device to capture a testing object image of the testing object; and calculate ratios of a target gray value to the gray value of a plurality of pixels of the testing object image to obtain a mapping table.

Abstract: A surface pattern detecting method includes: capturing a surface image of a sample element to be detected, wherein the surface image containing N grayscale pixels and wherein the N is a positive integer; selecting f×N pixels with small grayscale value based on a selection ratio f in order to define a pattern zone and further calculating a pattern mean of the pattern zone based on pixel amount and grayscale value of the pattern zone; selecting f×N pixels with big grayscale value in order to define a background zone and further calculating a background mean of the background zone based on pixel amount and grayscale value of the background zone; and determining whether the surface image has a defect based on the pattern means of the pattern zone and the background mean of the background zone.

Abstract: A surface pattern detecting method includes: capturing a surface image of a sample element to be detected, wherein the surface image containing N grayscale pixels and wherein the N is a positive integer; selecting f×N pixels with small grayscale value based on a selection ratio f in order to define a pattern zone and further calculating a pattern mean of the pattern zone based on pixel amount and grayscale value of the pattern zone; selecting f×N pixels with big grayscale value in order to define a background zone and further calculating a background mean of the background zone based on pixel amount and grayscale value of the background zone; and determining whether the surface image has a defect based on the pattern means of the pattern zone and the background mean of the background zone.