• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.681-682
• /
• 2021

본 논문에서는 소규모 데이터 셋의 이미지 분류 작업에서 모델 과적 합 및 비 수렴을 해결하고 분류의 정확도를 높이는 데 주로 사용되는 few-shot 학습을 기반으로 한 새로운 이미지 분류 방법을 제안합니다.

• International journal of advanced smart convergence
• /
• v.8 no.4
• /
• pp.75-81
• /
• 2019

Though recent advancement of deep learning methods have provided satisfactory results from large data domain, somehow yield poor performance on few-shot classification tasks. In order to train a model with strong performance, i.e. deep convolutional neural network, it depends heavily on huge dataset and the labeled classes of the dataset can be extremely humongous. The cost of human annotation and scarcity of the data among the classes have drastically limited the capability of current image classification model. On the contrary, humans are excellent in terms of learning or recognizing new unseen classes with merely small set of labeled examples. Few-shot learning aims to train a classification model with limited labeled samples to recognize new classes that have neverseen during training process. In this paper, we increase the backbone depth of the embedding network in orderto learn the variation between the intra-class. By increasing the network depth of the embedding module, we are able to achieve competitive performance due to the minimized intra-class variation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.5C
• /
• pp.514-522
• /
• 2003

Contrary to the previous methods, in this paper, we propose an enhanced shot change detection method using multiple features and binary decision tree. The previous methods usually used single feature and fixed threshold between consecutive frames. However, contents such as color, shape, background, and texture change simultaneously at shot change points in a video sequence. Therefore, in this paper, we detect the shot changes effectively using multiple features, which are supplementary each other, rather than using single feature. In order to classify the shot changes, we use binary classification tree. According to this classification result, we extract important features among the multiple features and obtain threshold value for each feature. We also perform the cross-validation and droop-case to verify the performance of our method. From an experimental result, it was revealed that the EI of our method performed average of 2% better than that of the conventional shot change detection methods.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.52-60
• /
• 2022

Few-shot learning is a sub-area of machine learning problems, which aims to classify target images that only contain a few labeled samples for training. As a representative few-shot learning method, the Prototypical network has been received much attention due to its simplicity and promising results. However, the Prototypical network uses the sample mean of samples from the same class as the prototypes of that class, which easily results in learning uncharacteristic features in the low-data scenery. In this study, we propose to use local descriptors (i.e., patches along the channel within feature maps) from the same class to explicitly obtain more representative prototypes for Prototypical Network so that significant intra-class feature information can be maintained and thus improving the classification performance on few-shot learning tasks. Experimental results on various benchmark datasets including mini-ImageNet, CUB-200-2011, and tiered-ImageNet show that the proposed method can learn more discriminative intra-class features by the local descriptors and obtain more generic prototype representations under the few-shot setting.

• Journal of information and communication convergence engineering
• /
• v.19 no.2
• /
• pp.79-83
• /
• 2021

This paper proposes a novel image classification method based on few-shot learning, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small datasets and improve the accuracy of classification. This method uses model structure optimization to extend the basic convolutional neural network (CNN) model and extracts more image features by adding convolutional layers, thereby improving the classification accuracy. We incorporated certain measures to improve the performance of the model. First, we used general methods such as setting a lower learning rate and shuffling to promote the rapid convergence of the model. Second, we used the data expansion technology to preprocess small datasets to increase the number of training data sets and suppress over-fitting. We applied the model to 10 monkey species and achieved outstanding performances. Experiments indicated that our proposed method achieved an accuracy of 87.92%, which is 26.1% higher than that of the traditional CNN method and 1.1% higher than that of the deep convolutional neural network ResNet50.

• Journal of Korea Multimedia Society
• /
• v.14 no.7
• /
• pp.858-865
• /
• 2011

In order to allow the user to efficiently browse, select, and retrieve a desired video part without having to deal directly with GBytes of compressed data, classification of shot motion characteristic has to be carried out as a preparation for such user interaction. The organization of video information for video database requires segmentation of a video into its constituent shots and their subsequent characterization in terms of content and camera movement in shot. In order to classify shot motion, it is a conventional way to use element of motion vector. However, there is a limit to estimate global camera motion because the way that uses motion vectors only represents local movement. For shot classification in terms of motion information, we propose a new scheme consisting of partial decoding of INTRA pictures and comparing the x, y displacement vector curve between the decoded I-frame and next P-frame in compressed video data.

• Smart Structures and Systems
• /
• v.33 no.1
• /
• pp.55-64
• /
• 2024

This paper proposes a fusion imaging-based coating-defect classification method for steel structures that uses zero-shot learning. In the proposed method, a halogen lamp generates heat energy on the coating surface of a steel structure, and the resulting heat responses are measured by an infrared (IR) camera, while photos of the coating surface are captured by a charge-coupled device (CCD) camera. The measured heat responses and visual images are then analyzed using zero-shot learning to classify the coating defects, and the estimated coating defects are visualized throughout the inspection surface of the steel structure. In contrast to older approaches to coating-defect classification that relied on visual inspection and were limited to surface defects, and older artificial neural network (ANN)-based methods that required large amounts of data for training and validation, the proposed method accurately classifies both internal and external defects and can classify coating defects for unobserved classes that are not included in the training. Additionally, the proposed model easily learns about additional classifying conditions, making it simple to add classes for problems of interest and field application. Based on the results of validation via field testing, the defect-type classification performance is improved 22.7% of accuracy by fusing visual and thermal imaging compared to using only a visual dataset. Furthermore, the classification accuracy of the proposed method on a test dataset with only trained classes is validated to be 100%. With word-embedding vectors for the labels of untrained classes, the classification accuracy of the proposed method is 86.4%.

• Journal of Korea Multimedia Society
• /
• v.7 no.7
• /
• pp.877-885
• /
• 2004

In this paper, we propose an enhancement shot change detection method using the neural net and the robust feature selection out of multiple features. The previous shot change detection methods usually used single feature and fixed threshold between consecutive frames. However, contents such as color, shape, background, and texture change simultaneously at shot change points in a video sequence. Therefore, in this paper, we detect the shot changes effectively using robust features, which are supplementary each other, rather than using single feature. In this paper, we use the typical CART (classification and regression tree) of data mining method to select the robust features, and the backpropagation neural net to determine the threshold of the each selected features. And to evaluation the performance of the robust feature selection, we compare the proposed method to the PCA(principal component analysis) method of the typical feature selection. According to the experimental result. it was revealed that the performance of our method had better that than the PCA method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.332-333
• /
• 2021

In this paper, we propose a new image classification method based on several trainings, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small data sets and to improve classification accuracy.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.576-586
• /
• 2020

Analyzing baseball games using sensors such as radars or riders is expensive. In this paper, we propose an algorithm to detect pitch shots and hit shots using baseball video and to generate ball trajectories within hit shots using camera movement. After the pitch shot and the hit shot detection using object detection and optical flow, we generate the transformation relationship between frames and ball locations in the frame, and calculates the ball trajectory. The performance of the proposed method is evaluated for three KBO baseball video sequences, and the detection accuracy and detection rate of pitch shot and hit shot were within 89-95 [%], and the average error for shot range was 13.6[m], The direction error was 7.5° and foul classification accuracy was 98.6%.