Sensory testing device and sensory testing method
An inspection device and sensory technology, applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve the problems of inspection automation using pattern recognition that cannot be completely solved
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach 1
[0047] First, use Figure 1 to Figure 11 , the sensory inspection device and the sensory inspection method in Embodiment 1 will be described.
[0048] figure 1 (a) is a block diagram showing a pseudo sample generation system of the sensory inspection device in Embodiment 1 of the present invention. figure 1 (b) is a block diagram showing the pattern recognition learning device of the sensory inspection device in Embodiment 1 of the present invention. In Embodiment 1, the pseudo-sample generating system is a pseudo-sample generating device.
[0049] exist figure 1 In (a), data such as images and sounds of good products stored in advance are read by the good product data input unit 1, and the extracted feature values are input through the feature value extraction unit 2 that performs filtering processing and feature value extraction. to the feature quantity space generation unit 3 . The feature quantity space generation unit 3 performs normalization and coordinate tran...
Embodiment approach 2
[0122] Next, use Figure 12 , the different features of the sensory inspection device and the sensory inspection method in Embodiment 2 from Embodiment 1 will be described.
[0123] Figure 12 It is a figure which shows the feature quantity space of Embodiment 2 of this invention. exist Figure 12 in, right with Figure 5 The same reference numerals are used for the same structural elements, and explanations are omitted.
[0124] Figure 12 (a) is the characteristic quantity of the initial sample. When selecting the initial sample, in Embodiment 1, the initial sample whose distance from the origin is a is selected, and the direction is random, but in this embodiment 2, the distance from the origin is a, and the direction is random. intervals become equally spaced initial samples.
[0125] exist Figure 12 In (b), the determination result of the initial sample is shown.
[0126] Figure 12 (c) is a diagram showing a method of generating feature values by the pseudo ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 