Diagnosis assisting device, and image processing method in diagnosis assisting device
A technology for image processing and supporting devices, which is applied in image data processing, diagnosis, image enhancement, etc., and can solve problems such as low robustness, pale skin, and no characteristic processing
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 approach
[0043] (Configuration of the first embodiment)
[0044] Such as figure 2As shown, the processing unit 12 of the first embodiment includes a color correction processing unit 121 . In order to perform color correction, the color correction processing unit 121 sets the peripheral portion of the photographed image other than the central portion with a high probability of disease as the measurement area, and sets the correction conversion target as skin color, and performs color correction processing. At this time, the color correction processing unit 121 regards the central part as the central circle of the photographed image, and obtains the Lp norms of the corresponding pixels for each RGB in the measurement area except the central circle, and uses the L2 norms of eR, eG, and eB To become 1, the coefficient k is used for normalization. After multiplying ec by 3^(1 / 2), take the reciprocal to set the color gain. Multiply the gain coefficient of RGB with each pixel to perform the...
no. 3 approach
[0097] (Configuration of the third embodiment)
[0098] Next, a third embodiment will be described. In the third embodiment, the dermoscopic image subjected to the color correction processing (normalization) of the first embodiment and / or the brightness correction processing (normalization) of the second embodiment is sent to a recognition system composed of a neural network. Machine input, using the results of machine learning to make inferences about the unknown disease of the subject of investigation. In this case, after normalizing the color and / or brightness of the skin color portion of the dermoscopic image, the normalized target value is subtracted and input to the neural network.
[0099] Figure 12 It is a block diagram showing the configuration of a diagnostic device 100A according to the third embodiment of the present invention. Such as Figure 12 As shown, a diagnostic device 100A according to the third embodiment of the present invention is connected to an im...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


