• 한국빅데이터학회지
• /
• 제8권2호
• /
• pp.133-140
• /
• 2023

본 연구는 20대와 한국인을 대상으로 한 건강관리 애플리케이션의 음식 이미지 분류 모델을 개선하는 것을 목표로 진행되었다. AI Hub에서 546,194개의 이미지를 수집하여 175개의 음식 클래스를 구성하였으며, ResNet 인공지능 모델을 학습하고 검증하였다. 추가적으로, 실제 촬영한 음식 이미지에 대한 인식 정확도가 상대적으로 낮게 나타나는 원인에 대해 고찰하고, 이를 해결하기 위한 방안으로 모델 성능을 최적화를 위한 다양한 방법을 분석하였다.

• 대한임베디드공학회논문지
• /
• 제19권1호
• /
• pp.47-55
• /
• 2024

We spend a lot of time in indoor space, and the space has a huge impact on our lives. Interior design plays a significant role to make an indoor space attractive and functional. However, it should consider a lot of complex elements such as color, pattern, and material etc. With the increasing demand for interior design, there is a growing need for technologies that analyze these design elements accurately and efficiently. To address this need, this study suggests a deep learning-based design analysis system. The proposed system consists of a semantic segmentation model that classifies spatial components and an image classification model that classifies attributes such as color, pattern, and material from the segmented components. Semantic segmentation model was trained using a dataset of 30000 personal indoor interior images collected for research, and during inference, the model separate the input image pixel into 34 categories. And experiments were conducted with various backbones in order to obtain the optimal performance of the deep learning model for the collected interior dataset. Finally, the model achieved good performance of 89.05% and 0.5768 in terms of accuracy and mean intersection over union (mIoU). In classification part convolutional neural network (CNN) model which has recorded high performance in other image recognition tasks was used. To improve the performance of the classification model we suggests an approach that how to handle data that has data imbalance and vulnerable to light intensity. Using our methods, we achieve satisfactory results in classifying interior design component attributes. In this paper, we propose indoor space design analysis system that automatically analyzes and classifies the attributes of indoor images using a deep learning-based model. This analysis system, used as a core module in the A.I interior recommendation service, can help users pursuing self-interior design to complete their designs more easily and efficiently.

• 대한의용생체공학회:의공학회지
• /
• 제43권1호
• /
• pp.45-51
• /
• 2022

The purpose of this study is to improve the classification accuracy compared to the existing InceptionV3 model by proposing a new model modified with the fully connected hierarchical structure of InceptionV3, which showed excellent performance in medical image classification. The data used for model training were trained after data augmentation on a total of 1026 chest X-ray images of patients diagnosed with normal heart and Cardiomegaly at Kyungpook National University Hospital. As a result of the experiment, the learning classification accuracy and loss of the InceptionV3 model were 99.57% and 1.42, and the accuracy and loss of the proposed model were 99.81% and 0.92. As a result of the classification performance evaluation for precision, recall, and F1 score of Inception V3, the precision of the normal heart was 78%, the recall rate was 100%, and the F1 score was 88. The classification accuracy for Cardiomegaly was 100%, the recall rate was 78%, and the F1 score was 88. On the other hand, in the case of the proposed model, the accuracy for a normal heart was 100%, the recall rate was 92%, and the F1 score was 96. The classification accuracy for Cardiomegaly was 95%, the recall rate was 100%, and the F1 score was 97. If the chest X-ray image for normal heart and Cardiomegaly can be classified using the model proposed based on the study results, better classification will be possible and the reliability of classification performance will gradually increase.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1287-1292
• /
• 2005

This paper presents an effective pattern classification model by designing an artificial neural network based pattern classifiers for face recognition. First, a RGB image inputted from a frame grabber is converted into a HSV image which is similar to the human beings' vision system. Then, the coarse facial region is extracted using the hue(H) and saturation(S) components except intensity(V) component which is sensitive to the environmental illumination. Next, the fine facial region extraction process is performed by matching with the edge and gray based templates. To make a light-invariant and qualified facial image, histogram equalization and intensity compensation processing using illumination plane are performed. The finally extracted and enhanced facial images are used for training the pattern classification models. The proposed H-ART2 model which has the hierarchical ART2 layers and F-LVQ model which is optimized by fuzzy membership make it possible to classify facial patterns by optimizing relations of clusters and searching clustered reference patterns effectively. Experimental results show that the proposed face recognition system is as good as the SVM model which is famous for face recognition field in recognition rate and even better in classification speed. Moreover high recognition rate could be acquired by combining the proposed neural classification models.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.557-558
• /
• 2021

본 논문에서는 소규모 데이터 세트의 이미지 분류 작업에서 모델 과적합 및 비수렴을 해결하고 분류 정확도를 향상시키는 데 주로 사용되는 CNN(Convolutional Neural Network) 기반의 새로운 이미지 분류 방법을 제안한다.

• 한국농공학회논문집
• /
• 제65권6호
• /
• pp.15-22
• /
• 2023

In this study, We conduct a comparative study of deep learning-based classification of agricultural field attributes using Tagged Image File (TIF) and Enhanced Compression Wavelet (ECW) images. The goal is to interpret and classify the attributes of agricultural fields by analyzing the differences between these two image formats. "FarmMap," initiated by the Ministry of Agriculture, Food and Rural Affairs in 2014, serves as the first digital map of agricultural land in South Korea. It comprises attributes such as paddy, field, orchard, agricultural facility and ginseng cultivation areas. For the purpose of comparing deep learning-based agricultural attribute classification, we consider the location and class information of objects, as well as the attribute information of FarmMap. We utilize the ResNet-50 instance segmentation model, which is suitable for this task, to conduct simulated experiments. The comparison of agricultural attribute classification between the two images is measured in terms of accuracy. The experimental results indicate that the accuracy of TIF images is 90.44%, while that of ECW images is 91.72%. The ECW image model demonstrates approximately 1.28% higher accuracy. However, statistical validation, specifically Wilcoxon rank-sum tests, did not reveal a significant difference in accuracy between the two images.

• Journal of information and communication convergence engineering
• /
• 제22권2호
• /
• pp.165-171
• /
• 2024

In this study, we present a novel approach for enhancing chest X-ray image classification (normal, Covid-19, edema, mass nodules, and pneumothorax) by combining contrastive learning and machine learning algorithms. A vast amount of unlabeled data was leveraged to learn representations so that data efficiency is improved as a means of addressing the limited availability of labeled data in X-ray images. Our approach involves training classification algorithms using the extracted features from a linear fine-tuned Momentum Contrast (MoCo) model. The MoCo architecture with a Resnet34, Resnet50, or Resnet101 backbone is trained to learn features from unlabeled data. Instead of only fine-tuning the linear classifier layer on the MoCopretrained model, we propose training nonlinear classifiers as substitutes for softmax in deep networks. The empirical results show that while the linear fine-tuned ImageNet-pretrained models achieved the highest accuracy of only 82.9% and the linear fine-tuned MoCo-pretrained models an increased highest accuracy of 84.8%, our proposed method offered a significant improvement and achieved the highest accuracy of 87.9%.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권24호
• /
• pp.10573-10576
• /
• 2015

Background: Accuracy in feature extraction is an important factor in image classification and retrieval. In this paper, a breast tissue density classification and image retrieval model is introduced for breast cancer detection based on thermographic images. The new method of thermographic image analysis for automated detection of high tumor risk areas, based on two-directional two-dimensional principal component analysis technique for feature extraction, and a support vector machine for thermographic image retrieval was tested on 400 images. The sensitivity and specificity of the model are 100% and 98%, respectively.

• 대한원격탐사학회지
• /
• 제19권6호
• /
• pp.479-490
• /
• 2003

This study proposed a modified anisotropic diffusion restoration for image classification. The anisotropic diffusion restoration uses a probabilistic model based on Markov random field, which represents geographical connectedness existing in many remotely sensed images, and restores them through an iterative diffusion processing. In every iteration, the bonding-strength coefficient associated with the spatial connectedness is adaptively estimated as a function of brightness gradient. The gradient function involves a constant called "temperature", which determines the amount of discontinuity and is continuously decreased in the iterations. In this study, the proposed method has been extensively evaluated using simulated images that were generated from various patterns. These patterns represent the types of natural and artificial land-use. The simulated images were restored by the modified anisotropic diffusion technique, and then classified by a multistage hierarchical clustering classification. The classification results were compared to them of the non-restored simulation images. The restoration with an appropriate temperature considerably reduces error in classification, especially for noisy images. This study made experiments on the satellite images remotely sensed on the Korean peninsula. The experimental results show that the proposed approach is also very effective on image classification in remote sensing.

• Design & Manufacturing
• /
• 제15권3호
• /
• pp.1-6
• /
• 2021

An artificial neural network model based on a deep learning algorithm is known to be more accurate than humans in image classification, but there is still a limit in the sense that there needs to be a lot of training data that can be called big data. Therefore, various techniques are being studied to build an artificial neural network model with high precision, even with small data. The transfer learning technique is assessed as an excellent alternative. As a result, the purpose of this study is to develop an artificial neural network system that can classify burr images of light guide plate products with 99% accuracy using transfer learning technique. Specifically, for the light guide plate product, 150 images of the normal product and the burr were taken at various angles, heights, positions, etc., respectively. Then, after the preprocessing of images such as thresholding and image augmentation, for a total of 3,300 images were generated. 2,970 images were separated for training, while the remaining 330 images were separated for model accuracy testing. For the transfer learning, a base model was developed using the NASNet-Large model that pre-trained 14 million ImageNet data. According to the final model accuracy test, the 99% accuracy in the image classification for training and test images was confirmed. Consequently, based on the results of this study, it is expected to help develop an integrated AI production management system by training not only the burr but also various defective images.