• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.537-547
• /
• 2023

In many domains, lack of data inhibits adoption of advanced machine learning models. Recently, Few-Shot Learning (FSL) has been actively studied to tackle this problem. Utilizing prior knowledge obtained through observations on related domains, FSL achieved significant performance with only a few samples. In this paper, we present a survey on FSL in terms of data augmentation, embedding and metric learning, and meta-learning. In addition to interesting researches, we also introduce major benchmark datasets. FSL is widely adopted in various domains, but we focus on image analysis in this paper.

• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.742-745
• /
• 2022

In this paper, we propose a hybrid image processing and deep learning-based method for detecting the presence of power lines in infrared images. Deep learning-based methods can learn feature vectors from a large number of data without much effort, resulting in outstanding performances in various fields. However, it is difficult to apply human intuition to the deep learning-based methods while image processing techniques can be used to apply human intuition. Based on these, we propose a method that exploits both advantages to detect the existence of power lines in infrared images. To this end, five methods have been applied and compared to find the most effective image processing technique for detecting the presence of power lines. As a result, the proposed method achieves 99.48% of accuracy which is higher than those of methods based on either image processing or deep learning.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.365-380
• /
• 2022

The target detection algorithm based on supervised learning is the current mainstream algorithm for target detection. A high-quality dataset is the prerequisite for the target detection algorithm to obtain good detection performance. The larger the number and quality of the dataset, the stronger the generalization ability of the model, that is, the dataset determines the upper limit of the model learning. The convolutional neural network optimizes the network parameters in a strong supervision method. The error is calculated by comparing the predicted frame with the manually labeled real frame, and then the error is passed into the network for continuous optimization. Strongly supervised learning mainly relies on a large number of images as models for continuous learning, so the number and quality of images directly affect the results of learning. This paper proposes a dataset STAR-24K (meaning a dataset for Space TArget Recognition with more than 24,000 images) for detecting common targets in space. Since there is currently no publicly available dataset for space target detection, we extracted some pictures from a series of channels such as pictures and videos released by the official websites of NASA (National Aeronautics and Space Administration) and ESA (The European Space Agency) and expanded them to 24,451 pictures. We evaluate popular object detection algorithms to build a benchmark. Our STAR-24K dataset is publicly available at https://github.com/Zzz-zcy/STAR-24K.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.403-408
• /
• 2018

Generally, a large data set is required for learning of deep learning. However, since it is not easy to create large data sets, there are a lot of techniques that make small data sets larger through data expansion such as rotation, flipping, and filtering. However, these simple techniques have limitation on extendibility because they are difficult to escape from the features already possessed. In order to solve this problem, we propose a method to acquire new image data by using existing data. This is done by retrieving and acquiring similar images using existing image data as a query of the content-based image retrieval (CBIR). Finally, we compare the performance of the base model with the model using CBIR.

• 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.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.44-46
• /
• 2021

Many cameras are used in real life, and they are often used for monitoring and crime prevention to check the situation of problems beyond just taking pictures for memories. Such surveillance and prevention are generally used only for simple storage, and in systems utilizing multiple cameras, utilizing additional features would require additional hardware specifications. In this paper, we add image input methods and post-object processing processes to process multiple image inputs from one hardware or server that perform object detection systems that deviate from typical image processing. The performance of the method is utilized in both learning and reasoning of the hardware performing deep learning, and allows improved image processing processes to be performed.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.111-121
• /
• 2021

As the main carrier of information, digital image is becoming more and more important. However, with the popularity of image acquisition equipment and the rapid development of image editing software, in recent years, digital image counterfeiting incidents have emerged one after another, which not only reduces the credibility of images, but also brings great negative impacts to society and individuals. Image copy-paste tampering is one of the most common types of image tampering, which is easy to operate and effective, and is often used to change the semantic information of digital images. In this paper, a method to protect the authenticity and integrity of image content by studying the tamper detection method of image copy and paste was proposed. In view of the excellent learning and analysis ability of deep learning, two tamper detection methods based on deep learning were proposed, which use the traces left by image processing operations to distinguish the tampered area from the original area in the image. A series of experimental results verified the rationality of the theoretical basis, the accuracy of tampering detection, location and classification.

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.280-287
• /
• 2023

Deep learning advancements can solve computer vision problems, but large-scale datasets are necessary for high accuracy. In this paper, we propose an image generation technique using object bounding boxes and image edge components. The object bounding boxes are extracted from the images through object detection, and image edge components are used as input values for the image generation model to create new image data. As results of experiments, the images generated by the proposed method demonstrated similar image quality to the source images in the image quality assessment, and also exhibited good performance during the deep learning training process.

• Electronics and Telecommunications Trends
• /
• v.33 no.4
• /
• pp.54-60
• /
• 2018

In this paper, we analyze the trends of deep-learning based plant data processing technologies. In recent years, the deep-learning technology has been widely applied to various AI tasks, such as vision (image classification, image segmentation, and so on) and natural language processing because it shows a higher performance on such tasks. The deep-leaning method is also applied to plant data processing tasks and shows a significant performance. We analyze and show how the deep-learning method is applied to plant data processing tasks and related industries.

• Journal of the Semiconductor & Display Technology
• /
• v.17 no.1
• /
• pp.71-75
• /
• 2018

Image enhancement is a necessary end essential step after taking a picture with a digital camera. Many different photo software packages attempt to automate this process with various auto enhancement techniques. This paper provides and implements a system that can learn a user's preferences and apply the preferences into the process of image enhancement. Five major components are applied to the implemented system, which are computing a distance metric, finding a training set, finding an optimal parameter set, training and finally enhancing the input image. To estimate the validity of the method, we carried out user studies, and the fact that the implemented system was preferred over the method without learning user preferences.