Deep hashing has realized very accurate similar image retrieval by learning the hash function via deep neural networks (DNN). Most deep hashing methods assume that queries originate from the same image dataset as the training images. However in practice, as the search system becomes older, it will encounter more query images that are not covered by the learned image dataset, To cope with this issue, we propose a solution named UIDH (Unsupervised Incremental Deep Hashing) that enables a deep hashing trained on one image dataset to learn an additional image dataset as new training data. First, UIDH obtains the initial hash function that outputs$K$-bit hash codes by learning the first image dataset with supervision. Later, UIDH learns the additional image dataset with unsupervised incremental learning and derives the second hash function that outputs$\frac{K}{2}$-bit hash codes. The final hash function in UIDH concatenates the upper half of the initial function with the second hash function. It maintains the high retrieval accuracy for the first dataset thanks to the initial supervised hashing and improves the similarity search for the additional dataset supported by the second unsupervised hashing. In this way, UIDH realizes an image search system that can treat the two dataset simultaneously. The novelty in UIDH is to handle the additional dataset without class labels.

In this paper, fourteen descriptors are evaluated for urban-rural classification of aerial images. Among these fourteen descriptors, eleven descriptors consist of texture-based, color-based con combination of these two descriptors. Rest three descriptors are based on dictionaries generated using the Lempel-Ziv-Welch (LZW) data compression algorithm. The classification is carried out using Support Vector Machine (SVM) with radial basis function as kernel function and KNN algorithm. The performance of these images descriptors are evaluated using accuracy, precision, sensitivity and specificity. From evaluation results, we conclude the Gabor descriptor combined with Dominant Color descriptor provides better performance, obtaining its accuracy more than 91%.

Locality-Sensitive Hashing (LSH) is a well-known approximate nearest-neighbor search algorithm for high-dimensional data. Though LSH searches nearest-neighbor points for a query very fast, LSH has a drawback that the space complexity is very large. For this reason, so as to apply LSH to a large dataset, it is crucial to implement LSH in distributed environments which consist of multiple nodes. One simple and natural method to implement LSH in the distributed environment is to have every node keep the same number of hash tables. However, this method increases remote accesses, because many nodes are accessed to access all the hash tables. Thus, this simple method will suffer from the long query response time, if the communication delay is the bottleneck. This paper proposes to reduce remote accesses by assigning hash buckets smartly to the nodes. In particular, our method assigns hash buckets from different hash tables to the same node, if the hash buckets store the same points. Due to this strategy, our method can access multiple hash buckets that should be accessed in processing a query with a single remote access, thereby decreasing remote accesses.

Video object segmentation is a task to distinguish the foreground from the background in videos. Most previous research on automatic video object segmentation based on graphcut segmentation uses the motion cue and the color cue to separate the background from the foreground. Consequently, the segmentation result deteriorates when the motion and/or the color becomes disordered, which typically occurs when a moving object stops and when a light is switched on/off. This paper proposes a new automatic video segmentation method robust to unstable motion and color. To achieve robustness, the graphcut segmentation is supported by the SURF feature, which is highly invariant to the change of scale, rotation, and luminance. In particular, our method matches the SURF features between two consecutive frames and modifies the segmentation result when the matched SURF features are assigned different labels.

This paper proposes PRDC-SSIS, a new compressibility-feature based semantic-sensitive image segmentation method using PRDC. One of the drawbacks of traditional signal (pixel-color) based image segmentation is the poor capability to capture the semantical information contained in the images. Because the semantic information tends to be carried by a set of neighboring pixels, rather than an individual pixel, we divide the image into patches and classify the patches based on their semantical contents. The crucial problem is classifying the patches into groups of similar patches according to their contents, and so we exploit the compressibility feature vector space of PRDC to accomplish this. An application of this method to an EO-image confirmed the proposed scheme can be carried out without any of the human-tailored target object models required by almost all traditional methods.

Tree is a data structure used to express various objects such as semistructured data and genes. When objects are represented as trees, computing tree similarity is essential for pattern recognition and retrieval. This paper considers the noisy subsequence tree recognition problem whose purpose is to recognize the original tree, given its noisy subsequence tree. Previous research on this problem relied on constrained tree edit distance to measure the dissimilarity. However, the number of relabelings must be predetermined to compute it. This paper proposes a new dissimilarity measure for this problem. Our dissimilarity measure is obtained by counting the node edit operations included in the unit-cost tree edit distance that contribute to the matching of node labels. The number of relabelings need not be specified to compute our dissimilarity measure. Moreover, our measure achieves more accurate recognition performance and faster execution speed than the constrained tree edit distance. Our measure is also useful to solve the tree inclusion problem which is the problem of deciding whether a tree includes another tree and shows the extent of approximate tree inclusion when a tree incompletely includes another tree. © 2011 Wiley Periodicals, Inc.

This paper presents a novel approach to discovering particular objects from a set of unannotated images. We aim to find discriminative feature sets that can effectively represent particular object classes (as opposed to object categories). We achieve this by mining correlated visual word sets from the bag-of-features model. Specifically, we consider that a visual word set belongs to the same object class if all its visual words consistently occur together in the same image. To efficiently find such sets we apply Min-LSH to the occurrence vector of the each visual word. An agglomerative hierarchical clustering is further performed to eliminate redundancy and obtain more representative sets. We also propose a simple and efficient strategy for quantizing the feature descriptors based on locality-sensitive hashing. By experiment, we show that our approach can efficiently discover objects against cluster and slight viewpoint variations.

AQM is a technique for congestion control such that a router notifies congestion to a TCP sender when congestion occurs. Almost no AQM algorithms ever take the RTT values of TCP connections into account in congestion control, despite they are essential parameters. This paper proposes a new AQM algorithm that exploits them explicitly by introducing a passive RTT estimation technique in a router. The simulation results show that our AQM stabilizes the queue length better than previous AQM algorithms

We propose data sharing facility for data intensive scientific research, "Data Reservoir"; which is optimized to transfer huge amount of data files between distant places fully Utilizing multi-gigabit backbone network. In addition, "Data Reservoir" can be used as an ordinary UNIX server in local network without any modification of server softwares. We use low-level protocol and hierarchical striping to realize (1) separation of bulk data transfer and local accesses by cashing, (2) file-system transparency, I.e. interoperable whatever in higher layer than disk driver, including file system. (3) scalability for network and storage. This paper shows our design, implementation using iSCSI protocol [1] and their performances for both 1Gbps model in the real network and 10Gbps model in our laboratory.