Distance Matrix Approach to Content Image Retrieval

As the volume of image data and the need of using it in various applications is growing significantly in the last days it brings a necessity of retrieval efficiency and effectiveness. Unfortunately, existing indexing methods are not applicable to a wide range of problem-oriented fields due to their operating time limitations and strong dependency on the traditional descriptors extracted from the image. To meet higher requirements, a novel distance-based indexing method for region-based image retrieval has been proposed and investigated. The method creates premises for considering embedded partitions of images to carry out the search with different refinement or roughening level and so to seek the image meaningful content.

Improving cross language information retrieval using corpus based query suggestion approach

Users seeking information may not find relevant information pertaining to their information need in a specific language. But information may be available in a language different from their own, but users may not know that language. Thus users may experience difficulty in accessing the information present in different languages. Since the retrieval process depends on the translation of the user query, there are many issues in getting the right translation of the user query. For a pair of languages chosen by a user, resources, like incomplete dictionary, inaccurate machine translation system may exist. These resources may be insufficient to map the query terms in one language to its equivalent terms in another language. Also for a given query, there might exist multiple correct translations. The underlying corpus evidence may suggest a clue to select a probable set of translations that could eventually perform a better information retrieval. In this paper, we present a cross language information retrieval approach to effectively retrieve information present in a language other than the language of the user query using the corpus driven query suggestion approach. The idea is to utilize the corpus based evidence of one language to improve the retrieval and re-ranking of news documents in the other language. We use FIRE corpora - Tamil and English news collections in our experiments and illustrate the effectiveness of the proposed cross language information retrieval approach.

Fast and effective focused retrieval

Building an efficient and an effective search engine is a very challenging task. In this paper, we present the efficiency and effectiveness of our search engine at the INEX 2009 Efficiency and Ad Hoc Tracks. We have developed a simple and effective pruning method for fast query evaluation, and used a two-step process for Ad Hoc retrieval. The overall results from both tracks show that our search engine performs very competitively in terms of both efficiency and effectiveness.

Document clustering algorithms, representations and evaluation for information retrieval

This thesis presents new methods for classification and thematic grouping of billions of web pages, at scales previously not achievable. This process is also known as document clustering, where similar documents are automatically associated with clusters that represent various distinct topic. These automatically discovered topics are in turn used to improve search engine performance by only searching the topics that are deemed relevant to particular user queries.

Text mining for screening efficiency? Testing within a Cochrane public health review

Background The requirement for dual screening of titles and abstracts to select papers to examine in full text can create a huge workload, not least when the topic is complex and a broad search strategy is required, resulting in a large number of results. An automated system to reduce this burden, while still assuring high accuracy, has the potential to provide huge efficiency savings within the review process. Objectives To undertake a direct comparison of manual screening with a semi‐automated process (priority screening) using a machine classifier. The research is being carried out as part of the current update of a population‐level public health review. Methods Authors have hand selected studies for the review update, in duplicate, using the standard Cochrane Handbook methodology. A retrospective analysis, simulating a quasi‐‘active learning’ process (whereby a classifier is repeatedly trained based on ‘manually’ labelled data) will be completed, using different starting parameters. Tests will be carried out to see how far different training sets, and the size of the training set, affect the classification performance; i.e. what percentage of papers would need to be manually screened to locate 100% of those papers included as a result of the traditional manual method. Results From a search retrieval set of 9555 papers, authors excluded 9494 papers at title/abstract and 52 at full text, leaving 9 papers for inclusion in the review update. The ability of the machine classifier to reduce the percentage of papers that need to be manually screened to identify all the included studies, under different training conditions, will be reported. Conclusions The findings of this study will be presented along with an estimate of any efficiency gains for the author team if the screening process can be semi‐automated using text mining methodology, along with a discussion of the implications for text mining in screening papers within complex health reviews.

Learning Embeddings for Indexing, Retrieval, and Classification, with Applications to Object and Shape Recognition in Image Databases

Nearest neighbor retrieval is the task of identifying, given a database of objects and a query object, the objects in the database that are the most similar to the query. Retrieving nearest neighbors is a necessary component of many practical applications, in fields as diverse as computer vision, pattern recognition, multimedia databases, bioinformatics, and computer networks. At the same time, finding nearest neighbors accurately and efficiently can be challenging, especially when the database contains a large number of objects, and when the underlying distance measure is computationally expensive. This thesis proposes new methods for improving the efficiency and accuracy of nearest neighbor retrieval and classification in spaces with computationally expensive distance measures. The proposed methods are domain-independent, and can be applied in arbitrary spaces, including non-Euclidean and non-metric spaces. In this thesis particular emphasis is given to computer vision applications related to object and shape recognition, where expensive non-Euclidean distance measures are often needed to achieve high accuracy. The first contribution of this thesis is the BoostMap algorithm for embedding arbitrary spaces into a vector space with a computationally efficient distance measure. Using this approach, an approximate set of nearest neighbors can be retrieved efficiently - often orders of magnitude faster than retrieval using the exact distance measure in the original space. The BoostMap algorithm has two key distinguishing features with respect to existing embedding methods. First, embedding construction explicitly maximizes the amount of nearest neighbor information preserved by the embedding. Second, embedding construction is treated as a machine learning problem, in contrast to existing methods that are based on geometric considerations. The second contribution is a method for constructing query-sensitive distance measures for the purposes of nearest neighbor retrieval and classification. In high-dimensional spaces, query-sensitive distance measures allow for automatic selection of the dimensions that are the most informative for each specific query object. It is shown theoretically and experimentally that query-sensitivity increases the modeling power of embeddings, allowing embeddings to capture a larger amount of the nearest neighbor structure of the original space. The third contribution is a method for speeding up nearest neighbor classification by combining multiple embedding-based nearest neighbor classifiers in a cascade. In a cascade, computationally efficient classifiers are used to quickly classify easy cases, and classifiers that are more computationally expensive and also more accurate are only applied to objects that are harder to classify. An interesting property of the proposed cascade method is that, under certain conditions, classification time actually decreases as the size of the database increases, a behavior that is in stark contrast to the behavior of typical nearest neighbor classification systems. The proposed methods are evaluated experimentally in several different applications: hand shape recognition, off-line character recognition, online character recognition, and efficient retrieval of time series. In all datasets, the proposed methods lead to significant improvements in accuracy and efficiency compared to existing state-of-the-art methods. In some datasets, the general-purpose methods introduced in this thesis even outperform domain-specific methods that have been custom-designed for such datasets.

Plate-specific gain map correction for the improvement of detective quantum efficiency in computed radiography.

PURPOSE: The purpose of this work is to improve the noise power spectrum (NPS), and thus the detective quantum efficiency (DQE), of computed radiography (CR) images by correcting for spatial gain variations specific to individual imaging plates. CR devices have not traditionally employed gain-map corrections, unlike the case with flat-panel detectors, because of the multiplicity of plates used with each reader. The lack of gain-map correction has limited the DQE(f) at higher exposures with CR. This current work describes a feasible solution to generating plate-specific gain maps. METHODS: Ten high-exposure open field images were taken with an RQA5 spectrum, using a sixth generation CR plate suspended in air without a cassette. Image values were converted to exposure, the plates registered using fiducial dots on the plate, the ten images averaged, and then high-pass filtered to remove low frequency contributions from field inhomogeneity. A gain-map was then produced by converting all pixel values in the average into fractions with mean of one. The resultant gain-map of the plate was used to normalize subsequent single images to correct for spatial gain fluctuation. To validate performance, the normalized NPS (NNPS) for all images was calculated both with and without the gain-map correction. Variations in the quality of correction due to exposure levels, beam voltage/spectrum, CR reader used, and registration were investigated. RESULTS: The NNPS with plate-specific gain-map correction showed improvement over the noncorrected case over the range of frequencies from 0.15 to 2.5 mm(-1). At high exposure (40 mR), NNPS was 50%-90% better with gain-map correction than without. A small further improvement in NNPS was seen from carefully registering the gain-map with subsequent images using small fiducial dots, because of slight misregistration during scanning. Further improvement was seen in the NNPS from scaling the gain map about the mean to account for different beam spectra. CONCLUSIONS: This study demonstrates that a simple gain-map can be used to correct for the fixed-pattern noise in a given plate and thus improve the DQE of CR imaging. Such a method could easily be implemented by manufacturers because each plate has a unique bar code and the gain-map for all plates associated with a reader could be stored for future retrieval. These experiments indicated that an improvement in NPS (and hence, DQE) is possible, depending on exposure level, over a wide range of frequencies with this technique.

Maintenance of a case-base for the retrieval of rotationally symmetric shapes for the design of metal castings

In this paper, we discuss the problem of maintenance of a CBR system for retrieval of rotationally symmetric shapes. The special feature of this system is that similarity is derived primarily from graph matching algorithms. The special problem of such a system is that it does not operate on search indices that may be derived from single cases and then used for visualisation and principle component analyses. Rather, the system is built on a similarity metric defined directly over pairs of cases. The problems of efficiency, consistency, redundancy, completeness and correctness are discussed for such a system. Performance measures for the CBR system are given, and the results for trials of the system are presented. The competence of the current case-base is discussed, with reference to a representation of cases as points in an n-dimensional feature space, and a Gramian visualisation. A refinement of the case base is performed as a result of the competence analysis and the performance of the case-base before and after refinement is compared.

FPGA-based minutia matching for biometric fingerprint image database retrieval

In this paper, a parallel-matching processor architecture with early jump-out (EJO) control is proposed to carry out high-speed biometric fingerprint database retrieval. The processor performs the fingerprint retrieval by using minutia point matching. An EJO method is applied to the proposed architecture to speed up the large database retrieval. The processor is implemented on a Xilinx Virtex-E, and occupies 6,825 slices and runs at up to 65 MHz. The software/hardware co-simulation benchmark with a database of 10,000 fingerprints verifies that the matching speed can achieve the rate of up to 1.22 million fingerprints per second. EJO results in about a 22% gain in computing efficiency.

Eps15 and Dap160 control synaptic vesicle membrane retrieval and synapse development

Epidermal growth factor receptor pathway substrate clone 15 (Eps15) is a protein implicated in endocytosis, endosomal protein sorting, and cytoskeletal organization. Its role is, however, still unclear, because of reasons including limitations of dominant-negative experiments and apparent redundancy with other endocytic proteins. We generated Drosophila eps15-null mutants and show that Eps15 is required for proper synaptic bouton development and normal levels of synaptic vesicle (SV) endocytosis. Consistent with a role in SV endocytosis, Eps15 moves from the center of synaptic boutons to the periphery in response to synaptic activity. The endocytic protein, Dap160/intersectin, is a major binding partner of Eps15, and eps15 mutants phenotypically resemble dap160 mutants. Analyses of eps15 dap160 double mutants suggest that Eps15 functions in concert with Dap160 during SV endocytosis. Based on these data, we hypothesize that Eps15 and Dap160 promote the efficiency of endocytosis from the plasma membrane by maintaining high concentrations of multiple endocytic proteins, including dynamin, at synapses.

Content Based Video Retrieval using SURF Descriptor

This paper presents a Robust Content Based Video Retrieval (CBVR) system. This system retrieves similar videos based on a local feature descriptor called SURF (Speeded Up Robust Feature). The higher dimensionality of SURF like feature descriptors causes huge storage consumption during indexing of video information. To achieve a dimensionality reduction on the SURF feature descriptor, this system employs a stochastic dimensionality reduction method and thus provides a model data for the videos. On retrieval, the model data of the test clip is classified to its similar videos using a minimum distance classifier. The performance of this system is evaluated using two different minimum distance classifiers during the retrieval stage. The experimental analyses performed on the system shows that the system has a retrieval performance of 78%. This system also analyses the performance efficiency of the low dimensional SURF descriptor.

A scalable re-ranking method for content-based image retrieval

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Mechanical thrombectomy for acute ischemic stroke: thrombus-device interaction, efficiency, and complications in vivo

BACKGROUND AND PURPOSE: Mechanical thrombectomy is a promising new modality of interventional stroke treatment. The various devices differ with regard to where they apply force on the thrombus, taking a proximal approach such as aspiration devices or a distal approach such as basket-like devices. The study compares the in vivo effectiveness and thrombus-device interaction of these 2 approaches. METHODS: Angiography and embolization with a radioopaque whole blood thrombus was performed in 10 swine. Mechanical thrombectomy was performed in 20 cranial vessels using a proximal aspiration device (Vasco35) and a distal basket-like device (Catch) with and without proximal balloon occlusion. Fifty-six retrieval attempts were made. RESULTS: The proximal device allowed fast repeated application with a low risk of thromboembolic events (3%) and vasospasm, but it had a significantly lower success rate (39.4%) in retrieving thrombotic material than the distal device (DD) (82.6%; odds ratio, 7.3; 95% CI, 2.0 to 26.4). The compaction of the thrombus during retrieval with DD increased the risk of vessel wall irritation significantly (P<0.01) and complicated retrieval into the guiding catheter. The number of embolic events was significantly higher with DD (26%; odds ratio, 11.3; 95% CI, 1.35 to 101.6) unless proximal balloon occlusion was used. CONCLUSIONS: The proximal and the distal approaches to mechanical thrombectomy proved to be effective at achieving recanalization of cranial vessels. The proximal device is faster in application and allowed repeated attempts with a low complication rate. The DD is more successful at removing thrombotic material, but its method of application and attendant thrombus compaction increase the risk of thromboembolic events and vasospasms.

Occlusion length is a crucial determinant of efficiency and complication rate in thrombectomy for acute ischemic stroke

BACKGROUND AND PURPOSE: Although mechanical thrombectomy (MT) has an encouragingly high recanalization rate in treating stroke, it is associated with severe complications of which the underlying factors have yet to be identified. Because MT is a mechanical approach, the mechanical properties of the thrombus might be crucial for its success. The present study assesses the effect of thrombus length on the in vivo effectiveness and complication rate of MT. MATERIALS AND METHODS: Angiography and embolization of 21 cranial vessels with radiopaque whole-blood thrombi 10, 20, and 40 mm in length (7 occlusions each) were performed in 7 swine. MT was carried out using a distal snarelike device (BCR Roadsaver) with proximal balloon occlusion. A total of 61 retrievals were attempted. RESULTS: In the group of 10-mm occlusions, 77.8% of the attempts achieved complete recanalisation. For longer occlusions, the success rates decreased significantly to 20% of attempts for 20-mm occlusions (odds ratio [OR], 14; 95% confidence interval [CI], 2.2-89.2) and 11.1% for 40-mm occlusions (OR, 28; 95% CI, 3.9-202.2; P < .005). The low success rates were largely due to complications associated with thrombus compaction during retrieval. Similarly, the rate of thromboembolic events increased from 0% in 10-mm occlusions to 14.8% in 40-mm occlusions. CONCLUSIONS: MT using a distal device proved to be a fast, effective, and safe procedure for recanalizing short (10-mm) occlusions in the animal model. However, occlusion length emerged as a crucial determinant for MT with a significant decrease in recanalization success per attempt and increased complication rates. These findings suggest limitations of MT in the clinical application.

Better Memory and Neural Efficiency in Young Apolipoprotein E 4 Carriers

The apolipoprotein E (APOE) epsilon4 allele is the major genetic risk factor for Alzheimer's disease, but an APOE effect on memory performance and memory-related neurophysiology in young, healthy subjects is unknown. We found an association of APOE epsilon4 with better episodic memory compared with APOE epsilon2 and epsilon3 in 340 young, healthy persons. Neuroimaging was performed in a subset of 34 memory-matched individuals to study genetic effects on memory-related brain activity independently of differential performance. E4 carriers decreased brain activity over 3 learning runs, whereas epsilon2 and epsilon3 carriers increased activity. This smaller neural investment of epsilon4 carriers into learning reappeared during retrieval: epsilon4 carriers exhibited reduced retrieval-related activity with equal retrieval performance. APOE isoforms had no differential effects on cognitive measures other than memory, brain volumes, and brain activity related to working memory. We suggest that APOE epsilon4 is associated with good episodic memory and an economic use of memory-related neural resources in young, healthy humans.