For correcting the color difference in machine vision imaging, all colors in the color space are usually used to train the correction model in traditional methods, which will lead to a complex training process of the model, long training time, and can not achieve high correction precision for each color. In order to solve these problems, a local color space correction scheme is proposed in this paper. In the scheme, the total color space is divided into smaller sub-color space based on color difference threshold and space distance respectively, and the colors in the sub-color space is corrected by polynomial regression method. The experimental results show that local color space correction has higher accuracy and more stable performance than total color space correction.
Learning weariness is a common psychological problem, which will affect students' learning effect and life quality. Currently, most ways to relieve the learning weariness require the intervention of a professional counselor or teacher, but these resources are often limited or difficult to access. In order to provide a low cost, high efficiency and easy to use tool for relieving the learning weariness, this paper introduces a dialogue system model based on text clustering algorithm and natural language processing algorithm to relieve the learning weariness of students. This dialogue system model provides learning emotion assessment function, learning weariness relieving function, and self-counseling advice function for students. Among them, the learning weariness relieving function is the highlight of this system model. Text clustering algorithm is the core technology of this function, which is able to classify the corpus according to different topics and train a specialized dialogue mod-el for each topic using natural language processing algorithm. In this way, when students ask questions, the learning weariness relieving function can select the most appropriate dialogue model to generate replies according to the topic of the question, so as to improve the quality and effect of the dialogue. In this paper, BLEU value is used as the evaluation index of the dialogue model, and F1-score is used as the evaluation index of text clustering model. Experimental results show that the dialogue system model can accurately distinguish the topic of the question and generate high quality replies. Therefore, this paper plans to improve the quality of the corpus used to train the models and try other data augmentation techniques in the future.