• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.6
• /
• pp.673-678
• /
• 2003

In this paper, we proposes a method for face recognition using HMM(hidden Markov model) and wavelet coefficients First, input images are compressed by using the multi-resolution analysis based on the discrete wavelet transform. And then, the wavelet coefficients obtained from each subband are used as feature vectors to construct the HMMs. In the recognition stage, we obtained higher recognition rate by summing of each recognition rate of wavelet subband. The usefulness of the proposed method was shown by comparing with conventional VQ and DCT-HMM ones. The experimental results show that the proposed method is more satisfactory than previous ones.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.475-491
• /
• 2021

With the recent increase in available high-resolution (< ~1 m) satellite SAR images, the demand for precise registration of SAR images is increasing in various fields including change detection. The registration between high-resolution SAR images acquired in different look angle is difficult due to speckle noise and geometric distortion caused by the characteristics of SAR images. In this study, registration is performed in two stages, coarse and fine, using the x-band SAR data imaged at staring spotlight mode of TerraSAR-X. For the coarse registration, a method combining the adaptive sampling method and SAR-SIFT (Scale Invariant Feature Transform) is applied, and three rigid methods (NCC: Normalized Cross Correlation, Phase Congruency-NCC, MI: Mutual Information) and one non-rigid (Gefolki: Geoscience extended Flow Optical Flow Lucas-Kanade Iterative), for the fine registration stage, was performed for performance comparison. The results were compared by using RMSE (Root Mean Square Error) and FSIM (Feature Similarity) index, and all rigid models showed poor results in all image combinations. It is confirmed that the rigid models have a large registration error in the rugged terrain area. As a result of applying the Gefolki algorithm, it was confirmed that the RMSE of Gefolki showed the best result as a 1~3 pixels, and the FSIM index also obtained a higher value than 0.02~0.03 compared to other rigid methods. It was confirmed that the mis-registration due to terrain effect could be sufficiently reduced by the Gefolki algorithm.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.121-126
• /
• 2004

An efficient multi face detection technique is proposed based on hierarchical context-free attention operators in which multiple faces are efficiently detected from a noisy and complex background. A noise-tolerant generalized symmetry transform (NTSGT) is applied hierarchically, as a context free attention operator, to the input pyramidal image for the high speed global location of the regions of face candidates (ROFCs) with a single mask. For the face verification, local NTGST is applied within each ROFC to confirm the existence of the detailed facial features. First, by globally applying NTGST which introduces the average pyramid method and focusing to the input image with complex background, ROFCs with recognizable resolution are detected robustly. Morphological operations are applied only to the each detected ROFCs to emphasize the facial features like eyes and lips. Then, eyes are detected by locally appling NTGST to the ROFCs and only faces are detected by verifying the existence of the geometrical features of the faces relatively to the location of eyes. The experimental results show that the proposed method can efficiently detect multiple faces from a noisy or complex background with 93.5% detection rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.6
• /
• pp.2230-2250
• /
• 2015

Multiple projectors with partially overlapping regions can be used to project a seamless image on a large projection surface. With the advent of high-resolution photography, such systems are gaining popularity. Experts set up such projection systems by subjectively identifying the types of errors induced by the system in the projected images and rectifying them by optimizing (correcting) the parameters associated with the system. This requires substantial time and effort, thus making it difficult to set up such systems. Moreover, comparing the performance of different multi-projector display (MPD) systems becomes difficult because of the subjective nature of evaluation. In this work, we present a framework to quantitatively determine the quality of an MPD system and any image projected using such a system. We have divided the quality assessment into geometric and photometric qualities. For geometric quality assessment, we use Feature Similarity Index (FSIM) and distance-based Scale Invariant Feature Transform (SIFT). For photometric quality assessment, we propose to use a measure incorporating Spectral Angle Mapper (SAM), Intensity Magnitude Ratio (IMR) and Perceptual Color Difference (ΔE). We have tested the proposed framework and demonstrated that it provides an acceptable method for both quantitative evaluation of MPD systems and estimation of the perceptual quality of any image projected by them.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1505-1514
• /
• 2022

Image matching is a crucial preprocessing step for effective utilization of multi-temporal and multi-sensor very high resolution (VHR) satellite images. Deep learning (DL) method which is attracting widespread interest has proven to be an efficient approach to measure the similarity between image pairs in quick and accurate manner by extracting complex and detailed features from satellite images. However, Image matching of VHR satellite images remains challenging due to limitations of DL models in which the results are depending on the quantity and quality of training dataset, as well as the difficulty of creating training dataset with VHR satellite images. Therefore, this study examines the feasibility of DL-based method in matching pair extraction which is the most time-consuming process during image registration. This paper also aims to analyze factors that affect the accuracy based on the configuration of training dataset, when developing training dataset from existing multi-sensor VHR image database with bias for DL-based image matching. For this purpose, the generated training dataset were composed of correct matching pairs and incorrect matching pairs by assigning true and false labels to image pairs extracted using a grid-based Scale Invariant Feature Transform (SIFT) algorithm for a total of 12 multi-temporal and multi-sensor VHR images. The Siamese convolutional neural network (SCNN), proposed for matching pair extraction on constructed training dataset, proceeds with model learning and measures similarities by passing two images in parallel to the two identical convolutional neural network structures. The results from this study confirm that data acquired from VHR satellite image database can be used as DL training dataset and indicate the potential to improve efficiency of the matching process by appropriate configuration of multi-sensor images. DL-based image matching techniques using multi-sensor VHR satellite images are expected to replace existing manual-based feature extraction methods based on its stable performance, thus further develop into an integrated DL-based image registration framework.

• Progress in Medical Physics
• /
• v.19 no.3
• /
• pp.150-156
• /
• 2008

An applied technique of contrast enhancement for X-ray image is proposed which is based on combined enhancement of scaling and wavelet coefficients in discrete wavelet transform space. Conventional contrast enhancement methods such as contrast limited adaptive histogram equalization (CLAHE), multi-scale image contrast amplification (MUSICA) and gamma correction were applied on scaling coefficients to enhance the contrast of an original. In order to enhance the detail as well as reduce the blurring caused by up scaling of contrast modified scale coefficients from lower resolution, the sigmoid manipulation function was used to manipulate wavelet coefficients. The contrast detail mammography (CDMAM) phantom was imaged and processed to measure the image line profile of results and contrast to noise ratio (CNR) comparatively. The proposed technique produced better results than direct application of various contrast enhancement methods on image itself. The proposed method can enhance contrast, and also suppress the amplification of noise components in a single process. It could be useful for various applications in medical, industrial and graphical images where contrast and detail are of importance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.4B
• /
• pp.771-782
• /
• 2000

In this paper, an H.263 video codec is implemented by adopting the concept of hardware and software co-design. Each module of the codec is investigated to find which approach between hardware and software is better to achieve real-time processing speed as well as flexibility. The hardware portion includes motion-related engines, such as motion estimation and compensation, and a memory control part. The remaining portion of theH.263 video codec is implemented in software using a RISC processor. This paper also introduces efficient design methods for hardware and software modules. In hardware, an area-efficient architecture for the motion estimator of a multi-resolution block matching algorithm using multiple candidates and spatial correlation in motion vector fields (MRMCS), is suggested to reduce the chip size. Software optimization techniques are also explored by using the statistics of transformed coefficients and the minimum sum of absolute difference (SAD)obtained from the motion estimator.

• The Journal of the Korea Contents Association
• /
• v.4 no.1
• /
• pp.18-23
• /
• 2004

In this paper, we propose a new visual feature extraction method for content-based image retrieval(CBIR) based on wavelet transform which has both spatial-frequency characteristic and multi-resolution characteristic. We extract visual features for each frequency band in wavelet transformation and use them to CBIR. The lowest frequency band involves spacial information of original image. We extract L feature vectors using fuzzy homogeneity in the wavelet domain, which consider both the wavelet coefficients and the spacial information of each coefficient. Also, we extract 3 feature vectors wing the energy values of high frequency bands, and store those to image database. As a query, we retrieve the most similar image from image database according to the 10 largest homograms(normalized fuzzy homogeneity vectors) and 3 energy values. Simulation results show that the proposed method has good accuracy in image retrieval using 90 texture images.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.7-10
• /
• 2006

Four programs, i.e. TRMM, ADEOS2, ASTER, and ALOS are going on in Japanese Earth Observation programs. TRMM and ASTER are operating well, and TRMM operation will be continued to 2009. ADEOS2 was failed, but AMSR-E on Aqua is operating. ALOS (Advanced Land Observing Satellite) was successfully launched on $24^{th}$ Jan. 2006. ALOS carries three instruments, i.e., PRISM (Panchromatic Remote Sensing Instrument for Stereo Mapping), AVNIR-2 (Advanced Visible and Near Infrared Radiometer), and PALSAR (Phased Array L band Synthetic Aperture Radar). PRISM is a 3 line panchromatic push broom scanner with 2.5m IFOV. AVNIR-2 is a 4 channel multi spectral scanner with 10m IFOV. PALSAR is a full polarimetric active phased array SAR. PALSAR has many observation modes including full polarimetric mode and scan SAR mode. After the unfortunate accident of ADEOS2, JAXA still have plans of Earth observation programs. Next generation satellites will be launched in 2008-2012 timeframe. They are GOSAT (Greenhouse Gas Observation Satellite), GCOM-W and GCOM-C (ADEOS-2 follow on), and GPM (Global Precipitation Mission) core satellite. GOSAT will carry 2 instruments, i.e. a green house gas sensor and a cloud/aerosol imager. The main sensor is a Fourier transform spectrometer (FTS) and covers 0.76 to 15 ${\mu}m$ region with 0.2 to 0.5 $cm^{-1}$ resolution. GPM is a joint project with NASA and will carry two instruments. JAXA will develop DPR (Dual frequency Precipitation Radar) which is a follow on of PR on TRMM. Another project is EarthCare. It is a joint project with ESA and JAXA is going to provide CPR (Cloud Profiling Radar). Discussions on future Earth Observation programs have been started including discussions on ALOS F/O.

• Journal of Broadcast Engineering
• /
• v.4 no.2
• /
• pp.144-154
• /
• 1999

The binomial sequences are family of orthogonal sequences that can be generated with remarkable simplicity-no multiplications are necessary. This paper introduces a class of non-recursive multidimensional filters for frequency-selective image processing without multiplication operations. The magnitude responses are narrow-band. approximately gaussian-shaped with center frequencies which can be positioned to yield low-pass. band-pass. or high-pass filtering. Algorithms for the efficient implementation of these filters in software or in hardware are described. Also. we show that the binomial QMFs are the maximally flat magnitude square Perfect Reconstruction paraunitary filters with good compression capability and these are shown to be wavelet filters as well. In wavelet transform the original image is decomposed at different scales using a pyramidal algorithm architecture. The decomposition is along the vertical and horizontal direction and maintains constant the number of pixels required to describe the images. An efficient perfect reconstruction binomial QMF-Wavelet signal decomposition structure is proposed. The technique provides a set of filter solutions with very good amplitude responses and band split. The proposed binomial QMF-filter structure is efficient, simple to implement on VLSl. and suitable for multi-resolution signal decomposition and coding applications.