This paper proposes an efficient iris localization method without using iris segmentation and circle fitting. Conventional iris localization methods first extract iris regions by using semantic segmentation methods such as U-Net. Afterward, the inner and outer iris circles are localized using the traditional circle fitting algorithm. However, this approach requires high-resolution encoder-decoder networks for iris segmentation, so it causes computational costs to be high. In addition, traditional circle fitting tends to be sensitive to noise in input images and fitting parameters, causing the iris recognition performance to be poor. To solve these problems, we propose an iris localization network (ILN), that can directly localize pupil and iris circles with eyelid points from a low-resolution iris image. We also introduce a pupil refinement network (PRN) to improve the accuracy of pupil localization. Experimental results show that the combination of ILN and PRN works in 34.5 ms for one iris image on a CPU, and its localization performance out-performs conventional iris segmentation methods. In addition, generalized evaluation results show that the proposed method has higher robustness for datasets in different domain than other segmentation methods. Furthermore, we also confirm that the proposed ILN and PRN improve the iris recognition accuracy.

This paper proposes a framework to train an artifact-free thin cloud removal model using Generative Adversarial Nets (GANs) with thick cloud masks. Satellite images are useful in various applications, however their exploitation is often limited by a presence of clouds. The proposed model can safely remove thin clouds for cloudy images while preserving thick clouds areas without creating undesired artifacts. In order to train the model, we propose a following framework divided in three blocks: generation of thick cloud masks for training images based on texture and spectrum analysis, selection of input-target couples of training images and training of the model using the GAN framework. The use of cloud masks for the training images allows the training of a model for clouds removal, robust to artifact generation in areas with thick clouds. Experimental results show that our model can actually avoid the generation of artifacts, and outperforms the conventional method in terms of SSIM index in testing.

This paper proposes a method of cloud shadow removal for multispectral images to retrieve the ground reflectance of areas shadowed by clouds. Cloud shadows are cast when incident direct solar irradiance gets attenuated by clouds. To retrieve the ground reflectance of the shadowed pixels, it is required to estimate pixel-wise attenuation factor for the solar irradiance. Unlike conventional methods, the proposed technique takes the physical model of cloud shadow formation into account to accurately estimate the attenuation factors. According to the physical model, the factors are derived from the transmittance of an occluding cloud. Visual and quantitative results demonstrate that the proposed method outperforms the well-known de-shadowing algorithm. The average correlation coefficient of the corrected image with a reference image is improved from 0.45 to 0.75 by the proposed method as compared to the conventional method. Further, the average spectral angle with a reference image is improved by 10%.

This paper presents a method for estimating the three dimensional (3D) position of Persistent Scatterers (PSs) for Persistent Scatterer Interferometric SAR (PS-InSAR) and a PS-InSAR analysis system. PSs are useful to monitor deformation of manmade structures with accuracy of millimeter range. However, SAR images include geometric distortions such as layovers or foreshortenings. These distortions cause errors in estimating the 3D positions (latitude, longitude and altitude) of PSs in the SAR images. Foreshortenings are corrected by conventional methods based on ortho-rectification. On the other hand, layovers still remain to be solved. In our method, both foreshortenings and layovers are corrected through estimating possible 3D positions of each PS (referred as “PS candidates”) by using Digital Surface Model (DSM) and the position of a satellite. The results by PS-InSAR analysis system show the validity of the proposed method.

This paper presents an image-based method for estimating path radiance by utilizing spectral characteristics of path radiance based on a physical model. Though image-based methods can estimate path radiance without using atmospheric properties, their accuracy is highly dependent on what is captured in a scene and hence inefficient in some cases. The proposed method corrects a path radiance spectrum estimated by the dark object subtraction (DOS) method so that the spectrum meets general spectral characteristics of path radiance. A simplified physical model of path radiance is introduced for this purpose. Experimental results show that the proposed method estimates path radiance more accurately than the DOS method in scenes including vegetation in particular. It is also shown that atmospheric correction incorporating the proposed method reduces correction errors by more than 60 percent on average in comparison with major atmospheric correction algorithms: percentage linear contrast stretch (PLCS) and quick atmospheric correction (QUAC).

This paper presents a novel method of enhancing image quality of face pictures using 3D and spectral information. Most conventional techniques directly work on the image data, shifting the skin color to a predefined skin tone, and thus do not take into account the effects of shape and lighting. The proposed method first recovers the 3D shape of a face in an input image using a 3D morphable model. Then, using color constancy and inverse rendering techniques, specularities and the true skin color, i.e., its spectral reflectance, are recovered. The quality of the input image is improved by matching the skin reflectance to a predefined reference and reducing the amount of specularities. The method realizes the enhancement in a more physically accurate manner compared to previous ones. Subjective experiments on image quality demonstrate the validity of the proposed method.

This paper proposes a new method for removing specularity from face images so that albedo (diffuse reflectivity) can be accurately estimated. Our method utilizes common structural properties of face images to estimate the Lambertian component (including shadows) without using albedo, then specularity is separated as the positive component of the difference between the estimated Lambertian component and the source image. Experimental results show that face-recognition performance is significantly improved by applying our new algorithm. Numerous previous face-recognition methods use 3D shape and albedo of an enrolled image for face recognition under variable pose and illumination conditions. However albedo used by the previous methods contained a residual of specularity from the enrolled image, which produced matching errors. Our algorithm is effective for solving this problem.

A new high dynamic range rendering (HDRR) suitable for YUV images is presented. The method overcomes the problem on saturation decrease caused by the conventional HDRRs for YUV images. U and V components are corrected with an approximating function that is designed to preserve the metric chroma in CIELAB before and after an HDRR. The function is derived from the relationship between the changes in the Y component and those in the chroma. The color differences between the images corrected by our method and the ideal images were found to be in an acceptable range, where they can be recognized as being the same color. Our method achieved the highest score in a subjective assessment of preserving the perceptual chroma when it was compared with other methods.

By noting gamma correction as one of the image quality adjustment parameters, the authors create an image quality enhancement support system capable of reflecting user subjectivity. In this study, the derivation of an optimum gamma value is formulated as an optimization problem. To reflect user subjectivity, an image quality enhancement support system is realized by interactive evolutionary computation. This technique is verified by comparing it with a manually derived gamma value, image quality, and derivation time.

We constructed a rack-mounted prototype photonic ATM switch based on the FRONTIERNET architecture. The advantages of the architecture are that its output-buffering scheme overcomes the bottlenecks that can occur when receiving and storing concurrent high-speed cells, and that there is no need to deal with contention resolution between input highways. The prototype has 16 input/output ports and 2.5 Gb/s transmission speed. Actually, six input ports and one output port are mounted in two racks. We demonstrated successful cell routing and buffering, and its stable operation, with 24-h bit-error-free switching operation. We also discussed problems to be solved in increasing the throughput of FRONTIERNET.

This paper describes large-capacity photonic ATM switching systems being developed that use FDM (or WDM) techniques. Our system is based on a simple star architecture with a modular structure. We show that it is possible to obtain a 320-Gb/s system that has enough S/N margin and can tolerate the polarization and frequency dependencies of optical devices. Our experiments using rack-mounted prototype modules to demonstrate the feasibility of our system, as well as successful 10-Gb/s 4/spl times/4 broadcast-and-select and 2.5-Gb/s 16/spl times/16 frequency-routing switch operations.

A novel computational algorithm is proposed for color constancy suitable to robot vision. A robot, or a computer, can exactly memorize image information observed in the past. Then it is natural to use more than one image to achieve color constancy. In the algorithm, it is possible to recover the illumination color and the reflectance color only based on the RGB values of two objects identified on two images. It requires no specific assumption on the scene. Experiments show the validity of the proposed algorithm.>