Learning model generation apparatus, image correction apparatus and method, and recording medium
A technology for learning models and generating devices, applied in machine learning, image communication, computing models, etc., can solve problems such as reducing the number of learning models, and achieve the effects of reducing the number, improving accuracy, and maintaining stable quality
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 Embodiment approach
[0062] Hereinafter, embodiments for implementing the technology of the present invention will be described in detail with reference to the drawings. In addition, in the image correction device 10 according to the present embodiment, as an example, a learning model for learning correction contents using image data before correction and image data after correction is generated, and the image data is processed using the generated learning model. The method of correcting the server is explained. However, it is not limited to this. The image correction device 10 may be, for example, a terminal such as a personal computer or a tablet, or a multifunction peripheral equipped with a scanning function, or the like. In addition, the learning model generation device according to the present embodiment will be described as being integrated with the image correction device 10 . However, it is not limited to this. The learning model generation device may be, for example, a terminal or ser...
no. 2 Embodiment approach
[0109] In the first embodiment, a method of classifying image information based on evaluation values calculated based on imaging conditions and generating a learning model has been described. In this embodiment, a method of classifying image information based on evaluation values and setting values to generate a learning model will be described. In addition, the hardware configuration of the image correction device 10 according to this embodiment (refer to figure 1 ), the functional structure of the image correction device 10 (refer to figure 2 ) and a schematic diagram showing the relationship between each set value and scaled value (refer to image 3) is the same as that of the first embodiment, so the description thereof will be omitted. In addition, a schematic diagram showing the relationship between evaluation values and classifications according to this embodiment (refer to Figure 4 ) is the same as that of the first embodiment, so the description thereof w...
no. 3 Embodiment approach
[0141] In the second embodiment, a method of selecting a learning model by calculating the order of priority based on the setting values of imaging conditions has been described. In this embodiment, a mode of expanding the range selected when selecting a learning model will be described. In addition, the hardware configuration of the image correction device 10 according to this embodiment (refer to figure 1 ), the functional structure of the image correction device 10 (refer to figure 2 ) and a schematic diagram showing the relationship between each set value and scaled value (refer to image 3 ) is the same as that of the first embodiment, so the description thereof will be omitted. In addition, a schematic diagram showing the relationship between evaluation values and classifications according to this embodiment (refer to Figure 4 ) and the flow chart of the learning model generation process (refer to Figure 5 ) and schematic diagrams showing the relationship betw...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More