• Journal of the Semiconductor & Display Technology
• /
• v.14 no.2
• /
• pp.53-59
• /
• 2015

Since the amount of digital image continues to grow in usage, users feel increased difficulty in finding specific images from the image collection. This paper proposes a novel image searching scheme that extracts the image feature using combination of Advanced SURF (Speed-Up Robust Feature) and DCD (Dominant Color Descriptor). The key point of this research is to provide a new feature extraction algorithm to improve the existing SURF method with removal of unnecessary feature in image retrieval, which can be adaptable to mobile system and efficiently run on the mobile environments. To evaluate the proposed scheme, we assessed the performance of simulation in term of average precision and F-score on two databases, commonly used in the field of image retrieval. The experimental results revealed that the proposed algorithm exhibited a significant improvement of over 14.4% in retrieval effectiveness, compared to OpenSURF. The main contribution of this paper is that the proposed approach achieves high accuracy and stability by using ASURF and DCD in searching for natural image on mobile platform.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2036-2038
• /
• 2001

In this paper, we propose the neural network based emotion recognition method for intelligently recognizing the human's emotion using vision system. In the proposed method, human's emotion is divided into four emotion (surprise, anger, happiness, sadness). Also, we use R,G,B(red, green, blue) color image data and the gray image data to get the highly trust rate of feature point extraction. For this, we propose an algorithm to extract four feature points (eyebrow, eye, nose, mouth) from the face image acquired by the color CCD camera and find some feature vectors from those. And then we apply back-prapagation algorithm to the secondary feature vector(position and distance among the feature points). Finally, we show the practical application possibility of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1418-1433
• /
• 2019

In computer graphics, 3D mesh segmentation is a challenging research field. This paper presents a 3D mesh model segmentation algorithm that focuses on removing exterior salient parts from the original 3D mesh model based on prominent feature points and marching plane. To begin with, the proposed approach uses multi-dimensional scaling to extract prominent feature points that reside on the tips of each exterior salient part of a given mesh. Subsequently, a set of planes intersect the 3D mesh; one is the marching plane, which start marching from prominent feature points. Through the marching process, local cross sections between marching plane and 3D mesh are extracted, subsequently, its corresponding area are calculated to represent local volumes of the 3D mesh model. As the boundary region of an exterior salient part generally lies on the location at which the local volume suddenly changes greatly, we can simply cut this location with the marching plane to separate this part from the mesh. We evaluated our algorithm on the Princeton Segmentation Benchmark, and the evaluation results show that our algorithm works well for some categories.

• Journal of Multimedia Information System
• /
• v.9 no.3
• /
• pp.177-182
• /
• 2022

A deep neural network (DNN) includes variables whose values keep on changing with the training process until it reaches the final point of convergence. These variables are the co-efficient of a polynomial expression to relate to the feature extraction process. In general, DNNs work in multiple 'dimensions' depending upon the number of channels and batches accounted for training. However, after the execution of feature extraction and before entering the SoftMax or other classifier, there is a conversion of features from multiple N-dimensions to a single vector form, where 'N' represents the number of activation channels. This usually happens in a Fully connected layer (FCL) or a dense layer. This reduced 2D feature is the subject of study for our analysis. For this, we have used the FCL, so the trained weights of this FCL will be used for the weight-class correlation analysis. The popular DNN models selected for our study are ResNet-101, VGG-19, and GoogleNet. These models' weights are directly used for fine-tuning (with all trained weights initially transferred) and scratch trained (with no weights transferred). Then the comparison is done by plotting the graph of feature distribution and the final FCL weights.

• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.247-257
• /
• 2021

This paper proposes a new technique for calibrating a multi-view RGB-D camera using a 3D (dimensional) skeleton. In order to calibrate a multi-view camera, consistent feature points are required. In addition, it is necessary to acquire accurate feature points in order to obtain a high-accuracy calibration result. We use the human skeleton as a feature point to calibrate a multi-view camera. The human skeleton can be easily obtained using state-of-the-art pose estimation algorithms. We propose an RGB-D-based calibration algorithm that uses the joint coordinates of the 3D skeleton obtained through the posture estimation algorithm as a feature point. Since the human body information captured by the multi-view camera may be incomplete, the skeleton predicted based on the image information acquired through it may be incomplete. After efficiently integrating a large number of incomplete skeletons into one skeleton, multi-view cameras can be calibrated by using the integrated skeleton to obtain a camera transformation matrix. In order to increase the accuracy of the calibration, multiple skeletons are used for optimization through temporal iterations. We demonstrate through experiments that a multi-view camera can be calibrated using a large number of incomplete skeletons.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.9
• /
• pp.49-55
• /
• 2019

This paper presents a marker image evaluation method based on analysis of object distribution in images and classification of images with repetitive patterns for effective marker-based augmented reality (AR) system development. We measure the variance of feature point coordinates to distinguish marker images that are vulnerable to occlusion, since object distribution affects object tracking performance according to partial occlusion in the images. Moreover, we propose a method to classify images suitable for object recognition and tracking based on the fact that the distributions of descriptor vectors among general images and repetitive-pattern images are significantly different. Comprehensive experiments for marker images confirm that the proposed marker image evaluation method distinguishes images vulnerable to occlusion and repetitive-pattern images very well. Furthermore, we suggest that scale-invariant feature transform (SIFT) is superior to speeded up robust features (SURF) in terms of object tracking in marker images. The proposed method provides users with suitability information for various images, and it helps AR systems to be realized more effectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.101-108
• /
• 2010

In this paper, we proposed a new lazy classifier with fuzzy k-nearest neighbors approach and feature selection which is based on reconstruction error. Reconstruction error is the performance index for locally linear reconstruction. When a new query point is given, fuzzy k-nearest neighbors approach defines the local area where the local classifier is available and assigns the weighting values to the data patterns which are involved within the local area. After defining the local area and assigning the weighting value, the feature selection is carried out to reduce the dimension of the feature space. When some features are selected in terms of the reconstruction error, the local classifier which is a sort of polynomial is developed using weighted least square estimation. In addition, the experimental application covers a comparative analysis including several previously commonly encountered methods such as standard neural networks, support vector machine, linear discriminant analysis, and C4.5 trees.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.57-64
• /
• 2009

This paper presents the hardware implementation of the pyramidal KLT(Kanade-Lucas-Tomasi) feature tracker. Because of its high computational complexity, it is not easy to implement a real-time KLT feature tracker using general-purpose processors. A hardware implementation of the pyramidal KLT feature tracker using FPGA(Field Programmable Gate Array) is described in this paper with emphasis on 1) adaptive adjustment of threshold in feature extraction under diverse lighting conditions, and 2) modification of the tracking algorithm to accomodate parallel processing and to overcome memory constraints such as capacity and bandwidth limitation. The effectiveness of the implementation was evaluated over ones produced by its software implementation. The throughput of the FPGA-based tracker was 30 frames/sec for video images with size of $720{\times}480$.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.65-70
• /
• 2013

Recently, the field of computer vision has been actively researched through digital image which can be easily generated as the development and expansion of digital camera technology. Especially, research that extracts and utilizes the feature in image has been actively carried out. The image stitching is a method that creates the high resolution image using features extract and match. Image stitching can be widely used in military and medical purposes as well as in variety fields of real life. In this paper, we have proposed efficient image stitching method using fast feature descriptor extraction and matching based on SURF algorithm. It can be accurately, and quickly found matching point by reduction of dimension of feature descriptor. The feature descriptor is generated by classifying of unnecessary minutiae in extracted features. To reduce the computational time and efficient match feature, we have reduced dimension of the descriptor and expanded orientation window. In our results, the processing time of feature matching and image stitching are faster than previous algorithms, and also that method can make natural-looking stitched image.

• Fashion & Textile Research Journal
• /
• v.11 no.5
• /
• pp.788-798
• /
• 2009

This study aims to develop a highly reproducible, optimal frame design algorithm using variations in the curvature of armscye circumference, which will provide the basics for remodeling the 3D human body shape with the concept of reverse design used to develop total contents for the apparel industry. 1. The results of the experiment proved that ratio value was significantly efficient than absolute value of curvature variation to extract feature points in the armscye circumference 2. For the shoulder(1st and 2nd quadrant) and front armhole(3rd quadrant) parts of the armscye circumference, frame remodeling with the positive point of inflection led to the completion of a highly reproducible frame. 3. Similarly, even for the rear armhole part(4th quadrant) in the armscye circumference, it was found that frame remodeling using the positive maximum point of inflection resulted in highly reproducible body shape with the maximum point of inflection situated within the range of split angles $305^{\circ}{\sim}330^{\circ}$, while frame remodeling using simultaneously the two largest points of inflection including maximum point of inflection led to highly reproducible body shape with the maximum point of inflection out of the range $305^{\circ}{\sim}330^{\circ}$. 4. Based upon the optimal frame design algorithm developed in this study, section-specific feature points in the armscye circumference were extracted depending on the rate of curvature variation and remodeling with spline curves was conducted. The results indicate a remarkably high reproducibility(98.6%) and suggest that the algorithm developed in this study is suitable for human body modeling.