• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1140-1145
• /
• 2003

Image normalization is one of the important areas in pattern recognition. Also, log-polar images are useful in the sense that their image data size is reduced dramatically comparing with conventional images and it is possible to develop faster pattern recognition algorithms. Especially, the log-polar image is very similar with the structure of human eyes. However, there are almost no researches on pattern recognition using the log-polar images while a number of researches on visual tracking have been executed. We propose an image normalization technique of log-polar images using momentums applicable for affine-invariant pattern recognition. We handle basic distortions of an image including translation, rotation, scaling, and skew of a log-polar image. The algorithm is experimented in a PC-based real-time vision system successfully.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.8
• /
• pp.88-100
• /
• 1999

Detecting human face and facial landmarks automatically in an image is as essential step to a fully automatic face recognition system. In this paper, we present a new approach to detect automatically face and its eyes of input image with scale and rotation variations of faces by using an intensity based template matching with a single log-polar face template. In a template-based matching it is necessary to normalize the scale changes and rotations of an input image to a template ones. The log-polar mapping which simulates space-variant human visual system converts scale changes and rotations of input image into constant horizontal and cyclic vertical shifts in the output plane. Intelligent use of this property allows us to shift of the candidate log-polar faces mapped at various fixation points of an input image to be matched to a template over the log-polar plane. Thus, the proposed method eliminates the need of adapting multitemplate and multiresolution schemes, which inevitably give rise to intensive computation involved to cope with scale and rotation variations of faces. Through this scale and rotation involved to cope with scale and method can lead to detecting face and its eyes simultaneously. Experimental results on a database of 795 images show over 98% detection rate.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.675-678
• /
• 2000

This paper presents a parametric line equation on the log-polar mapped plane to detect the straight lines in an original image. The log-polar edge image used in Hough transform is constructed by combining the edge images of both fovea and periphery. The foveal edge image detected by a Sobel mask on the Cartesian plane is transformed to the log-polar plane by forward mapping but the edge detection of the peripheral region is obtained by directly applying the newly developed mask to the log-polar plane. This paper also proposes a analytic method then determining a border between the fovea and the periphery regions.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.4
• /
• pp.455-461
• /
• 2002

This paper presents a new parametric log line equation of polar form for Hough transform in log-polar plane, in which it can remove the well-known unboundedness problem of Hough parameters. Bolduc's method is used to generate a log-polar image dividing the fovea and periphery from a Cartesian image. Edges of the fovea and periphery are detected by using the Sobel mask and the proposed space-variant gradient mask, and are combined in the log-polar plane. The sampled points that might constitute a log line are quite sparse in a deep peripheral region due to severe under-sampling, which is an inherent property of LPM. To cope with such under-sampling, we determine the values of cumulative cells in Hough space by using the space-variant weighting. In our experiments, the proposed method demonstrates its validity of detecting not only the lines passing through both the fovea and periphery but also the lines in a deep periphery.

• Proceedings of the IEEK Conference
• /
• 2000.06c
• /
• pp.181-184
• /
• 2000

In this paper, we propose new features for describing texture images by using multi-channel Gabor filter and log-polar transform based on human visual system (HVS). Gabor features are extracted by the mean and standard deviation of energy in Gabor response, followed by Fourier series extension. Log-polar features are extracted by log-polar transform and projection. The proposed texture descriptor performs reasonably well with less number of features than other texture descriptors, which has been verified by experiments using some texture images of MPEG-7 data set.

• International Journal of Precision Engineering and Manufacturing
• /
• v.9 no.4
• /
• pp.45-50
• /
• 2008

The Fourier-Mellin transform is the theoretical basis for the translation, rotation, and scale invariance of an image. However, its implementation requires a log-polar map of the original image, which requires logarithmic sampling of a radial variable in that image. This means that the mapping process is accompanied by considerable loss of data. To solve this problem, we propose a dual log-polar map that uses both a forward image map and a reverse image map simultaneously. Data loss due to the forward map sub-sampling can be offset by the reverse map. This is the first step in creating an invertible log-polar map. Experimental results have demonstrated the effectiveness of the proposed scheme.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.2
• /
• pp.1-10
• /
• 2002

This paper presents the new template based human face recognition methods to improve the recognition performance against scale and in-plane rotation variations of face images. To enhance the recognition performance, the templates are generated by linear or nonlinear operation on multiple images including different scales and rotations of faces. As the invariant features to allow for scale and rotation variations of face images, we adopt the affine transformation, the log-polar mapping, and the log-polar image based FFT. The proposed recognition methods are evaluated in terms of the recognition rate and the processing time. Experimental results show that the proposed template based methods lead to higher recognition rate than the single image based one. The affine transformation based face recognition method shows marginally higher recognition rate than those of the log-polar mapping based method and the log-polar image based FFT, while, in the aspect of processing time, the log-polar mapping based method is the fastest one.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2471-2473
• /
• 2003

인간의 안구는 색과 모양을 식별하는 데에 관여하는 원추 세포와 물체의 명암을 구분하는 간상 세포로 구성되어지는 시세포를 가진다. 망막 위에 분포되어 있는 시세포들은 시축을 중심으로 각기 다른 밀도로 분포 되어 있다. 특히 광축과 만나는 중심 지역은 Fovea라고 하는 직경 1mm 정도의 작은 우물을 이루고 있는데 원추 세포들이 고해상도로 분포되어 있고 시신경과 일대일로 연결되어 있어 시각 처리의 중심이 된다. 특히, 글자나 물체를 인식하기 위해 인간은 대상물을 응시하여 대상물의 영상이 Fovca영역에 맺히도록 추적 운동을 계속한다. 본 논문에서는 인간의 눈과 유사한 망막 모델의 하나인 Log-polar Image를 이용한 물체 인식을 위해 물체를 Log-polar Image Plane의 중심에 위치시키기 위한 모멘텀(Momentum)기반 정합 알고리즘(Alignment Algorithm)을 제시한다. 이는 눈동자 운동이 가능한 능동형 시각 장치의 Tracking 및 Pursuit 동작 중에 밭생하는 추적 오차를 보상함으로써 운동 중에도 효과적인 물체 인식이 가능하게 한다. 또한, 물체를 Log-polar Image Plane의 중심에 위치시킴으로써 물체의 위치 이동, 회전이동 그리고 크기 변화에 무관하게 물체를 인식한 수 있음을 제시한다.

• ETRI Journal
• /
• v.28 no.6
• /
• pp.819-821
• /
• 2006

Log-polar coordinate image space is proposed as a solution for the problem of unbounded accumulator space in the automatic detection of vanishing points. The proposed method can detect vanishing points at high speed under small memory requirements, as opposed to conventional image space based methods.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.33A no.6
• /
• pp.178-188
• /
• 1996

In this paper, we propose a new opto-digital object recognition system which has rotation, scale, and shift invariant characteristics. The fourier power spectrum of the object image is modified to get shift invariance. The log-polar transform is used for rotation and scale invariance. And the decision of similarities is performed by nonlinear joint transform correlator (NJTC) that can control the ratio of phase and amplitude signals. Experimental verification of th eproposed optical object recognition system is presented.