A Two-Stage Learning Method of CNN and K-means RGB Cluster for Sentiment Classification of Images

이미지 감성분류를 위한 CNN과 K-means RGB Cluster 이-단계 학습 방안

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.

이미지 분류에서 딥러닝 모형을 사용하는 가장 큰 이유는 이미지의 전체적인 정보에서 각 지역 특징을 추출하여 서로의 관계를 고려할 수 있기 때문이다. 하지만 이미지의 지역 특징이 없는 감정 이미지 데이터는 CNN 모델이 적합하지 않을 수 있다. 이러한 감정 이미지 분류의 어려움을 해결하기 위하여 매년 많은 연구자들이 감정 이미지에 적합한 CNN기반 아키텍처를 제시하고 있다. 색깔과 사람 감정간의 관계에 대한 연구들도 수행되었으며, 색깔에 따라 다른 감정이 유도된다는 결과들이 도출되었다. 딥러닝을 활용한 연구에서도 색깔정보를 활용하여 이미지 감성분류에 적용하는 연구들이 있어왔으며, 이미지만을 가지고 분류 모형을 학습한 경우보다 이미지의 색깔 정보를 추가로 활용한 경우가 이미지 감성 분류 정확도를 더 높일 수 있었다. 본 연구는 사람이 이미지의 감정을 분류하는 기준 중 많은 부분을 차지하는 색감을 이용하여 이미지 감성 분류 정확도를 향상시키는 방안을 제안한다. 이미지의 RGB 값에 K 평균 군집화 방안을 적용하여 이미지를 대표하는 색을 추출하여, 각 감성 클래스 별 해당 색깔이 나올 확률을 가중치 식으로 변형 후 CNN 모델의 최종 Layer에 적용하는 이-단계 학습방안을 구현하였다. 이미지 데이터는 6가지 감정으로 분류되는 Emotion6와 8가지 감정으로 분류되는 Artphoto를 사용하였다. 학습에 사용한 CNN 모델은 Densenet169, Mnasnet, Resnet101, Resnet152, Vgg19를 사용하였으며, 성능 평가는 5겹 교차검증으로 CNN 모델에 이-단계 학습 방안을 적용하여 전후 성과를 비교하였다. CNN 아키텍처만을 활용한 경우보다 색 속성에서 추출한 정보를 함께 사용하였을 때 더 좋은 분류 정확도를 보였다.