Shin'ichi Satoh

The SR-tree: an index structure for high-dimensional nearest neighbor queries

Recently, similarity queries on feature vectors have been widely used to perform content-based retrieval of images. To apply this technique to large databases, it is required to develop multidimensional index structures supporting nearest neighbor queries efficiently. The SS-tree had been proposed for this purpose and is known to outperform other index structures such as the R*-tree and the K-D-B-tree. One of its most important features is that it employs bounding spheres rather than bounding rectangles for the shape of regions. However, we demonstrate in this paper that bounding spheres occupy much larger volume than bounding rectangles with high-dimensional data and that this reduces search efficiency. To overcome this drawback, we propose a new index structure called the SR-tree (Sphere/Rectangle-tree) which integrates bounding spheres and bounding rectangles. A region of the SR-tree is specified by the intersection of a bounding sphere and a bounding rectangle. Incorporating bounding rectangles permits neighborhoods to be partitioned into smaller regions than the SS-tree and improves the disjointness among regions. This enhances the performance on nearest neighbor queries especially for high-dimensional and non-uniform data which can be practical in actual image/video similarity indexing. We include the performance test results the verify this advantage of the SR-tree and show that the SR-tree outperforms both the SS-tree and the R*-tree.

Name-It: naming and detecting faces in news videos

We developed Name-It, a system that associates faces and names in news videos. It processes information from the videos and can infer possible name candidates for a given face or locate a face in news videos by name. To accomplish this task, the system takes a multimodal video analysis approach: face sequence extraction and similarity evaluation from videos, name extraction from transcripts, and video-caption recognition.

Video OCR: indexing digital new libraries by recognition of superimposed captions

Abstract. The automatic extraction and recognition of news captions and annotations can be of great help locating topics of interest in digital news video libraries. To achieve this goal, we present a technique, called Video OCR (Optical Character Reader), which detects, extracts, and reads text areas in digital video data. In this paper, we address problems, describe the method by which Video OCR operates, and suggest applications for its use in digital news archives. To solve two problems of character recognition for videos, low-resolution characters and extremely complex backgrounds, we apply an interpolation filter, multi-frame integration and character extraction filters. Character segmentation is performed by a recognition-based segmentation method, and intermediate character recognition results are used to improve the segmentation. We also include a method for locating text areas using text-like properties and the use of a language-based postprocessing technique to increase word recognition rates. The overall recognition results are satisfactory for use in news indexing. Performing Video OCR on news video and combining its results with other video understanding techniques will improve the overall understanding of the news video content.

Endothelin and the production of cerebral vasospasm in dogs

We attempted to determine whether or not endothelin (ET) plays a physiological role in cerebral vasospasm. ET (10(-11) - 3 x 10(-8) M) induced a concentration-dependent contraction in isolated canine basilar arteries. Intracisternal injection of 10 to 1,000 pmol ET into dogs induced a dose-dependent decrease in the basilar artery diameter, as measured angiographically on the 1st day. On the 3rd day after the injection of ET (10 pmol), the diameter of the basilar artery had diminished to 76% of the value seen in the control. There were no effects on blood pressure or heart rate. Thus, ET seems to be a potent constrictor of cerebral arteries in vivo, and these effects are long-lasting.

Effects of fasudil in acute ischemic stroke: Results of a prospective placebo-controlled double-blind trial

BACKGROUND A multicenter, double-blind, placebo-controlled study was conducted to assess the efficacy and safety of fasudil, a Rho-kinase inhibitor (RKI), in the treatment of acute ischemic stroke. METHODS A total of 160 patients, who were able to receive drug treatment within 48 h of acute ischemic stroke onset were enrolled. Patients received either 60 mg fasudil or a placebo (saline) by intravenous injection over 60 min, twice daily for 14 days. The primary end points were neurological status at 2 weeks after the start of treatment, and clinical outcome at 1 month after the onset of symptoms. RESULTS Fasudil treatment resulted in significantly greater improvements in both neurological functions (p=0.0013), and clinical outcome (p=0.0015). There were no serious adverse events reported in the fasudil group. The average trough value (12 h values) of active metabolite hydroxyfasudil, another RKI, in healthy elderly volunteers receiving 60 mg of fasudil was 0.077 microM-a concentration well above that needed to inhibit Rho-kinase (0.025-0.05 microM). CONCLUSION Treatment with fasudil within 48 h of acute ischemic stroke onset significantly improved the patients clinical outcome. This study found fasudil to be a useful and safe drug for patients with acute ischemic stroke. Further evaluations, for example, 3-month functional outcomes in a larger clinical trial, may help to define the efficacy of fasudil in acute ischemic stroke.

Name-It: association of face and name in video

This paper proposes a novel approach to extract meaningful content information from video by collaborative integration of image understanding and natural language processing. As an actual example, we developed a system that associates faces and names in videos, called Name-It, which is given news videos as a knowledge source, then automatically extracts face and name association as content information. The system can infer the name of a given unknown face image, or guess faces which are likely to have the name given to the system. This paper explains the method with several successful matching results which reveal effectiveness in integrating heterogeneous techniques as well as the importance of real content information extraction from video, especially face-name association.

Comparative evaluation of face sequence matching for content-based video access

The paper presents a comparative evaluation of matching methods of face sequences obtained from actual videos. Face information is quite important in videos, especially in news programs, dramas, and movies. Accurate face sequence matching enables many multimedia applications including content-based face retrieval, automated face annotation, video authoring, etc. However, face sequences in videos are subject to variation in lighting condition, pose, facial expression, etc., which cause difficulty in face matching. In order to cope with this problem, several face sequence matching methods are proposed by extending face still image matching, traditional pattern recognition, and recent pattern recognition techniques. They are expected to be applicable to face sequences extracted from actual videos. The performance of these methods is evaluated as the accuracy of face sequence annotation using the methods. The accuracy is evaluated using a considerable amount of actual drama videos. The evaluation results reveal merits and demerits of these methods, and indicate future research directions of face matching for videos.

A New Model of Cerebral Microthrombosis in Rats and the Neuroprotective Effect of a Rho-Kinase Inhibitor

Background and Purpose The aim of this study was to develop a new model of stroke based on endothelial damage and thrombotic occlusion in a perforating artery, leading to small cerebral infarcts and neurological deficits in rats. Moreover, the neuroprotective efficacy of fasudil, a rho-kinase inhibitor, was investigated in this model. Methods Fifty-six male Sprague-Dawley rats were used in the present study. Rats were anesthetized with sodium pentobarbital, and 100 &mgr;g of sodium laurate was injected into the left internal carotid artery on days 1 and 3. The thrombus induction and consequent of ischemic brain damage were examined by histopathological analyses and neurological deficit scoring in a posture reflex test. To investigate the neuroprotective effects of fasudil, 1 or 10 mg/kg was administered intraperitoneally 5 minutes after the first injection of sodium laurate and once daily thereafter on the following 2 days. Results One hour after the injection of sodium laurate, microscopic examination of phosphotungstic acid hematoxylin–stained sections (n=5) revealed that microthrombi containing fibrin strands obstructed the perforating arteries in the ipsilateral hemisphere. Under a transmission electron microscope (n=6), endothelial cells appeared exfoliated and the vascular lumen was obstructed by a thrombus composed of degranulated platelets, fibrin, leukocytes, and erythrocytes. No evidence of endothelial cell damage or thrombus could be found in the ipsilateral side of the pial artery (middle cerebral artery). Twenty-four hours after the second injection of sodium laurate (day 4), 13 of 15 rats (86.6%) showed mild to severe neurological deficits. Multiple small cerebral infarcts were observed in the hippocampus, cortex, and thalamus. Treatment with fasudil (1 and 10 mg/kg, n=15 each) resulted in a significant improvement in neurological deficits. Fasudil also significantly reduced the area of cerebral infarction. Conclusions We present a new model of stroke in rats, in which the perforating arteries are selectively occluded by microthrombi. This model is useful to investigate the pathophysiology and treatment of small cerebral infarction, which is caused by perforating arterial occlusive diseases such as lacunar infarcts. Fasudil may be beneficial in the treatment of acute ischemic stroke.

Building compact local pairwise codebook with joint feature space clustering

This paper presents a simple, yet effective method of building a codebook for pairs of spatially close SIFT descriptors. Integrating such codebook into the popular bag-of-words model encodes local spatial information which otherwise cannot be represented with just individual SIFT descriptors. Many previous pairing techniques first quantize the descriptors to learn a set of visual words before they are actually paired. Our approach contrasts with theirs in that each pair of spatially close descriptors is represented as a data point in a joint feature space first and then clustering is applied to build a codebook called Local Pairwise Codebook (LPC). It is advantageous over the previous approaches in that feature selection over quadratic number of possible pairs of visual words is not required and feature aggregation is implicitly performed to achieve a compact codebook. This is all done in an unsupervised manner. Experimental results on challenging datasets, namely 15 Scenes, 67 Indoors, Caltech-101, Caltech-256 and MSRCv2 demonstrate that LPC outperforms the baselines and performs competitively against the state-of-the-art techniques in scene and object categorization tasks where a large number of categories need to be recognized.

Cooking navi: assistant for daily cooking in kitchen

We are developing a cooking navigation system, which helps even a novice user to cook several recipes in parallel without failure, while improving an advanced users skill further. To realize this, the system optimizes the cooking procedure considering the following restrictions: (1) Duration of cooking, (2) Accuracy of cooking, and (3) Learning effect, by providing appropriate instructions to users at the right timing, making full use of multimedia information. The users should be able to cook perfectly and comfortably just by following the text, video and audio provided by the system. According to the result of a preliminary experiment, all users from novice to experienced cooks could finish two dishes in parallel while enjoyeing the cooking very much. The result of a questionnaire shows the effectiveness of the multimedia navigation that we propose.