• International Journal of Internet, Broadcasting and Communication
• /
• v.10 no.4
• /
• pp.50-64
• /
• 2018

This paper describes a visual object detection approach utilizing ensemble based machine learning. Object detection methods employing 1D features have the benefit of fast calculation speed. However, for real image with complex background, detection accuracy and performance are degraded. In this paper, we propose an ensemble learning algorithm that combines a 1D feature classifier and 2D DNF (Disjunctive Normal Form) classifier to improve the object detection performance in a single input image. Also, to improve the computing efficiency and accuracy, we propose a feature selecting method to reduce the computing time and ensemble algorithm by combining the 1D features and 2D DNF features. In the verification experiments, we selected the Haar-like feature as the 1D image descriptor, and demonstrated the performance of the algorithm on a few datasets such as face and vehicle.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.3
• /
• pp.16-25
• /
• 1998

In this paper, we propose features extraction method using Rough sets theory for efficient data classifications in hyperspectral environment. First, analyze the properties of multispectral image data, then select the most efficient bands using discemibility of Rough sets theory based on analysis results. The proposed method is applied Landsat TM image data, from this, we verify the equivalence of traditional bands selection method by band features and bands selection method using Rough sets theory that pmposed in this paper. Finally, we present theoretical basis to features extraction in hyperspectral environment.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.13 no.4
• /
• pp.683-688
• /
• 2010

The ability to navigate autonomously in off-road terrain is the most critical technology needed for Unmanned Ground Vehicles(UGV). In this paper, we present a method for vision-based terrain cover classification using DCT features. To classify the terrain, we acquire image from a CCD sensor, then the image is divided into fixed size of blocks. And each block transformed into DCT image then extracts features which reflect frequency band characteristics. Neural network classifier is used to classify the features. The proposed method is validated and verified through many experiments and we compare it with wavelet feature based method. The results show that the proposed method is more efficiently classify the terrain-cover than wavelet feature based one.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2154-2168
• /
• 2022

Our work addresses the issues associated with usage of the semantic features by Bag of Words model, which requires construction of the dictionary. Extracting the relevant features and clustering them into code book or dictionary is computationally intensive and requires large storage area. Hence we propose to use a simple distribution of multiple shape based features, which is a mixture of gradients, radius and slope angles requiring very less computational cost and storage requirements but can serve as an equivalent image representative. The experimental work conducted on PASCAL VOC 2007 dataset exhibits marginally closer performance in terms of accuracy with the Bag of Word model using Self Organizing Map for clustering and very significant computational gain.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.3
• /
• pp.153-163
• /
• 2016

Local feature extraction methods for images and videos are widely applied in the fields of image understanding and computer vision. However, robust features are detected differently when using the latest feature detectors and descriptors because of diverse image environments. This paper analyzes various feature extraction methods by summarizing algorithms, specifying properties, and comparing performance. We analyze eight feature extraction methods. The performance of feature extraction in various image environments is compared and evaluated. As a result, the feature detectors and descriptors can be used adaptively for image sequences captured under various image environments. Also, the evaluation of feature detectors and descriptors can be applied to driving assistance systems, closed circuit televisions (CCTVs), robot vision, etc.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3823-3840
• /
• 2020

Recently, auto-encoder has emerged as the most popular method in convolutional neural network (CNN) based image compression and has achieved impressive performance. In the traditional auto-encoder based image compression model, the encoder simply sends the features of last layer to the decoder, which cannot allocate bits over different spatial regions in an efficient way. Besides, these methods do not fully exploit the contextual information under different receptive fields for better reconstruction performance. In this paper, to solve these issues, a novel auto-encoder model is designed for image compression, which can effectively transmit the hierarchical features of the encoder to the decoder. Specifically, we first propose an adaptive bit-allocation strategy, which can adaptively select an importance channel. Then, we conduct the multiply operation on the generated importance mask and the features of the last layer in our proposed encoder to achieve efficient bit allocation. Moreover, we present an additional novel perceptual loss function for more accurate image details. Extensive experiments demonstrated that the proposed model can achieve significant superiority compared with JPEG and JPEG2000 both in both subjective and objective quality. Besides, our model shows better performance than the state-of-the-art convolutional neural network (CNN)-based image compression methods in terms of PSNR.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.5
• /
• pp.910-924
• /
• 2010

As Internet usage has increased, the risk of adolescents being exposed to adult content and harmful information on the Internet has also risen. To help prevent adolescents accessing this content, a novel detection method for adult images is proposed. The proposed method involves three steps. First, the Image Of Interest (IOI) is extracted from the image background. Second, the IOI is distinguished from the segmented image using a novel weighting mask, and it is determined to be acceptable or unacceptable. Finally, the features (color and texture) of the IOI or original image are compared to a critical value; if they exceed that value then the image is deemed to be an adult image. A Receiver Operating Characteristic (ROC) curve analysis was performed to define this optimal critical value. And, the textural features are identified using a gray level co-occurrence matrix. The proposed method increased the precision level of detection by applying a novel weighting mask and a receiver operating characteristic curve. To demonstrate the effectiveness of the proposed method, 2850 adult and non-adult images were used for experimentation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.656-658
• /
• 2022

The purpose of infrared and visible image fusion is to integrate images of different modes with different details into a result image with rich information, which is convenient for high-level computer vision task. Considering many deep networks only work in a single scale, this paper proposes a novel image fusion based on three-scale dense network to preserve the content and key target features from the input images in the fused image. It comprises an encoder, a three-scale block, a fused strategy and a decoder, which can capture incredibly rich background details and prominent target details. The encoder is used to extract three-scale dense features from the source images for the initial image fusion. Then, a fusion strategy called l₁-norm to fuse features of different scales. Finally, the fused image is reconstructed by decoding network. Compared with the existing methods, the proposed method can achieve state-of-the-art fusion performance in subjective observation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2483-2504
• /
• 2023

Most existing low-light enhancement algorithms either use a large number of training parameters or lack generalization to real-world scenarios. This paper presents a novel lightweight and robust pixel-wise polynomial approximation-based deep network for low-light image enhancement. For mapping the low-light image to the enhanced image, pixel-wise higher-order polynomials are employed. A deep convolution network is used to estimate the coefficients of these higher-order polynomials. The proposed network uses multiple branches to estimate pixel values based on different receptive fields. With a smaller receptive field, the first branch enhanced local features, the second and third branches focused on medium-level features, and the last branch enhanced global features. The low-light image is downsampled by the factor of 2b-1 (b is the branch number) and fed as input to each branch. After combining the outputs of each branch, the final enhanced image is obtained. A comprehensive evaluation of our proposed network on six publicly available no-reference test datasets shows that it outperforms state-of-the-art methods on both quantitative and qualitative measures.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.2
• /
• pp.47-54
• /
• 2011

This paper describes the method to reduce the time-cost for depth estimation of an image by learning, on the basis of the Genetic Algorithm, the image's features. The depth information is estimated from the relationship among features such as the energy value of an image and the gradient of the texture etc. The estimation-time increases due to the large dimension of an image's features used in the estimating process. And the use of the features without consideration of their importance can have an adverse effect on the performance. So, it is necessary to reduce the dimension of an image's features based on the significance of each feature. Evaluation of the method proposed in this paper using benchmark data provided by Stanford University found that the time-cost for feature extraction and depth estimation improved by 60% and the accuracy was increased by 0.4% on average and up to 2.5%.