Hierarchical indexing structure for efficient similarity search in video retrieval

With the rapid increase in both centralized video archives and distributed WWW video resources, content-based video retrieval is gaining its importance. To support such applications efficiently, content-based video indexing must be addressed. Typically, each video is represented by a sequence of frames. Due to the high dimensionality of frame representation and the large number of frames, video indexing introduces an additional degree of complexity. In this paper, we address the problem of content-based video indexing and propose an efficient solution, called the Ordered VA-File (OVA-File) based on the VA-file. OVA-File is a hierarchical structure and has two novel features: 1) partitioning the whole file into slices such that only a small number of slices are accessed and checked during k Nearest Neighbor (kNN) search and 2) efficient handling of insertions of new vectors into the OVA-File, such that the average distance between the new vectors and those approximations near that position is minimized. To facilitate a search, we present an efficient approximate kNN algorithm named Ordered VA-LOW (OVA-LOW) based on the proposed OVA-File. OVA-LOW first chooses possible OVA-Slices by ranking the distances between their corresponding centers and the query vector, and then visits all approximations in the selected OVA-Slices to work out approximate kNN. The number of possible OVA-Slices is controlled by a user-defined parameter delta. By adjusting delta, OVA-LOW provides a trade-off between the query cost and the result quality. Query by video clip consisting of multiple frames is also discussed. Extensive experimental studies using real video data sets were conducted and the results showed that our methods can yield a significant speed-up over an existing VA-file-based method and iDistance with high query result quality. Furthermore, by incorporating temporal correlation of video content, our methods achieved much more efficient performance.

Multigradient field-active contour model for multilayer boundary detection of ultrasound rectal wall image

Extraction and reconstruction of rectal wall structures from an ultrasound image is helpful for surgeons in rectal clinical diagnosis and 3-D reconstruction of rectal structures from ultrasound images. The primary task is to extract the boundary of the muscular layers on the rectal wall. However, due to the low SNR from ultrasound imaging and the thin muscular layer structure of the rectum, this boundary detection task remains a challenge. An active contour model is an effective high-level model, which has been used successfully to aid the tasks of object representation and recognition in many image-processing applications. We present a novel multigradient field active contour algorithm with an extended ability for multiple-object detection, which overcomes some limitations of ordinary active contour models—"snakes." The core part in the algorithm is the proposal of multigradient vector fields, which are used to replace image forces in kinetic function for alternative constraints on the deformation of active contour, thereby partially solving the initialization limitation of active contour for rectal wall boundary detection. An adaptive expanding force is also added to the model to help the active contour go through the homogenous region in the image. The efficacy of the model is explained and tested on the boundary detection of a ring-shaped image, a synthetic image, and an ultrasound image. The experimental results show that the proposed multigradient field-active contour is feasible for multilayer boundary detection of rectal wall

The assessment of oral cytology utilizing ploidy analysis and virtual microscopy for the early detection of epithelial dysplasia and neoplasia in oral mucosal lesions

Oral squamous cell carcinoma (OSCC) is associated with high morbidity and mortality which is due, at least in part, to late detection. Precancerous and cancerous oral lesions may mimic any number of benign oral lesions, and as such may be left without investigation and treatment until they are well advanced. Over the past several years there has been renewed interest in oral cytology as an adjuvant clinical tool in the investigation of oral mucosal lesions. The purpose of the present study was to compare the usefulness of ploidy analysis after Feulgen stained cytological thin-prep specimens with traditional incisional biopsy and routine histopathological examination for the assessment of the pre-malignant potential of oral mucosal lesions. An analysis of the cytological specimens was undertaken with virtual microscopy which allowed for rapid and thorough analysis of the complete cytological specimen. 100 healthy individuals between 30 and 70 years of age, who were non-smokers, non-drinkers and not taking any medication, had cytological specimens collected from both the buccal mucosa and lateral margin of tongue to establish normal cytology parameters within a control population. Patients with a presumptive clinical diagnosis of lichen planus, leukoplakia or OSCC had lesional cytological samples taken prior to their diagnostic biopsy. Standardised thin preparations were prepared and each specimen stained by both Feuglen and Papanicolau methods. High speed scanning of the complete slide at 40X magnification was undertaken using the Aperio Scanscope TM and the green channel of the resultant image was analysed after threshold segmentation to isolate only nuclei and the integrated optical density of each nucleus taken as a gross measure of the DNA content (ploidy). Preliminary results reveal that ploidy assessment of oral cytology holds great promise as an adjunctive prognostic factor in the analysis of the malignant potential of oral mucosal lesions.

Automatic building detection using the Dempster-Shafer algorithm

An approach and strategy for automatic detection of buildings from aerial images using combined image analysis and interpretation techniques is described in this paper. It is undertaken in several steps. A dense DSM is obtained by stereo image matching and then the results of multi-band classification, the DSM, and Normalized Difference Vegetation Index (NDVI) are used to reveal preliminary building interest areas. From these areas, a shape modeling algorithm has been used to precisely delineate their boundaries. The Dempster-Shafer data fusion technique is then applied to detect buildings from the combination of three data sources by a statistically-based classification. A number of test areas, which include buildings of different sizes, shape, and roof color have been investigated. The tests are encouraging and demonstrate that all processes in this system are important for effective building detection.

Computational methods for the detection of facial palsy

We are developing a telemedicine application which offers automated diagnosis of facial (Bell's) palsy through a Web service. We used a test data set of 43 images of facial palsy patients and 44 normal people to develop the automatic recognition algorithm. Three different image pre-processing methods were used. Machine learning techniques (support vector machine, SVM) were used to examine the difference between the two halves of the face. If there was a sufficient difference, then the SVM recognized facial palsy. Otherwise, if the halves were roughly symmetrical, the SVM classified the image as normal. It was found that the facial palsy images had a greater Hamming Distance than the normal images, indicating greater asymmetry. The median distance in the normal group was 331 (interquartile range 277-435) and the median distance in the facial palsy group was 509 (interquartile range 334-703). This difference was significant (P

Off-line signature verification and forgery detection system based on fuzzy modeling

This paper presents an innovative approach for signature verification and forgery detection based on fuzzy modeling. The signature image is binarized and resized to a fixed size window and is then thinned. The thinned image is then partitioned into a fixed number of eight sub-images called boxes. This partition is done using the horizontal density approximation approach. Each sub-image is then further resized and again partitioned into twelve further sub-images using the uniform partitioning approach. The features of consideration are normalized vector angle (α) from each box. Each feature extracted from sample signatures gives rise to a fuzzy set. Since the choice of a proper fuzzification function is crucial for verification, we have devised a new fuzzification function with structural parameters, which is able to adapt to the variations in fuzzy sets. This function is employed to develop a complete forgery detection and verification system.

A method to lower the detection limit for optical beat signals from a frequency-dithered stabilized laser

A narrow absorption feature in an atomic or molecular gas (such as iodine or methane) is used as the frequency reference in many stabilized lasers. As part of the stabilization scheme an optical frequency dither is applied to the laser. In optical heterodyne experiments, this dither is transferred to the RF beat signal, reducing the spectral power density and hence the signal to noise ratio over that in the absence of dither. We removed the dither by mixing the raw beat signal with a dithered local oscillator signal. When the dither waveform is matched to that of the reference laser the output signal from the mixer is rendered dither free. Application of this method to a Winters iodine-stabilized helium-neon laser reduced the bandwidth of the beat signal from 6 MHz to 390 kHz, thereby lowering the detection threshold from 5 pW of laser power to 3 pW. In addition, a simple signal detection model is developed which predicts similar threshold reductions.

Development and evaluation of neural network freeway incident detection models using field data

This paper discusses a multi-layer feedforward (MLF) neural network incident detection model that was developed and evaluated using field data. In contrast to published neural network incident detection models which relied on simulated or limited field data for model development and testing, the model described in this paper was trained and tested on a real-world data set of 100 incidents. The model uses speed, flow and occupancy data measured at dual stations, averaged across all lanes and only from time interval t. The off-line performance of the model is reported under both incident and non-incident conditions. The incident detection performance of the model is reported based on a validation-test data set of 40 incidents that were independent of the 60 incidents used for training. The false alarm rates of the model are evaluated based on non-incident data that were collected from a freeway section which was video-taped for a period of 33 days. A comparative evaluation between the neural network model and the incident detection model in operation on Melbourne's freeways is also presented. The results of the comparative performance evaluation clearly demonstrate the substantial improvement in incident detection performance obtained by the neural network model. The paper also presents additional results that demonstrate how improvements in model performance can be achieved using variable decision thresholds. Finally, the model's fault-tolerance under conditions of corrupt or missing data is investigated and the impact of loop detector failure/malfunction on the performance of the trained model is evaluated and discussed. The results presented in this paper provide a comprehensive evaluation of the developed model and confirm that neural network models can provide fast and reliable incident detection on freeways. (C) 1997 Elsevier Science Ltd. All rights reserved.

Specific PCR based detection of Phytophthora medicaginis using the intergenic spacer region of the ribosomal DNA

A technique based on the polymerase chain reaction (PCR) for the specific detection of Phytophthora medicaginis was developed using nucleotide sequence information of the ribosomal DNA (rDNA) regions. The complete IGS 2 region between the 5 S gene of one rDNA repeat and the small subunit of the adjacent repeat was sequenced for P. medicaginis and related species. The entire nucleotide sequence length of the IGS 2 of P. medicaginis was 3566 bp. A pair of oligonucleotide primers (PPED04 and PPED05), which allowed amplification of a specific fragment (364 bp) within the IGS 2 of P. medicaginis using the PCR, was designed. Specific amplification of this fragment from P. medicaginis was highly sensitive, detecting template DNA as low as 4 ng and in a host-pathogen DNA ratio of 1000000:1. Specific PCR amplification using PPED04 and PPED05 was successful in detecting P. medicaginis in lucerne stems infected under glasshouse conditions and field infected lucerne roots. The procedures developed in this work have application to improved identification and detection of a wide range of Phytophthora spp. in plants and soil.

Vascular leakage stimulates phenotype alteration in ocular cells, contributing to the pathology of proliferative vitreoretinopathy

Plasma leaking from damaged retinal blood vessels can have a significant impact on the pathologies of the posterior segment of the eye. Inflammation in the eye and metabolic change resulting from diabetes mellitus causes vascular leakage with alteration of the phenotype of retinal pigment epithelial (RPE) cells and fibrocytes, resulting in changes in cell function. Phenotypically altered cells then significantly contribute to the pathogenesis of retinopathies by being incorporated into tractional membranes in the vitreous, where they secrete matrix molecules, such as fibronectin, and express altered cell surface antigens. We hypothesize that there is a direct relationship between the leaking of plasma and the proliferation and phenotypic change of RPE cells and fibroblasts, thus exacerbating the pathology of retinal disease. If the hypothesis is correct, control of vascular leakage becomes an important target of therapy in proliferative vitreoretinopathy.

Improved one-step solid-phase extraction method for morphine, morphine-3-glucuronide, and morphine-6-glucuronide from plasma and quantitation using high-performance liquid chromatography with electrochemical detection

This communication describes an improved one-step solid-phase extraction method for the recovery of morphine (M), morphine-3-glucuronide (M3G), and morphine-6-glucuronide (M6G) from human plasma with reduced coextraction of endogenous plasma constituents, compared to that of the authors' previously reported method. The magnitude of the peak caused by endogenous plasma components in the chromatogram that eluted immediately before the retention time of M3G has been reduced (similar to 80%) significantly (p < 0.01) while achieving high extraction efficiencies for the compounds of interest, viz morphine, M6G, and M3G (93.8 +/- 2.5, 91.7 +/- 1.7, and 93.1 +/- 2.2%, respectively). Furthermore, when the improved solid-phase extraction method was used, the extraction cartridge-derived late-eluting peak (retention time 90 to 100 minutes) reported in our previous method, was no longer present in the plasma extracts. Therefore the combined effect of reducing the recovery of the endogenous components of plasma that chromatographed just before the retention time of M3G and the removal of the late-eluting, extraction cartridge-derived peak has resulted in a decrease in the chromatographic run-time to 20 minutes, thereby increasing the sample throughput by up to 100%.