- CONTENT BASED VIDEO RETRIEVAL BASED ON HDWT AND SPARSE REPRESENTATION
Sajad Mohamadzadeh, Hassan Farsi
Video retrieval has recently attracted a lot of research attention due to the exponential growth of video datasets and the internet. Content based video retrieval (CBVR) systems are very useful for a wide range of applications with several type of data such as visual, audio and metadata. In this paper, we are only using the visual information from the video. Shot boundary detection, key frame extraction, and video retrieval are three important parts of CBVR systems. In this paper, we have modified and proposed new methods for the three important parts of our CBVR system. Meanwhile, the local and global color, texture, and motion features of the video are extracted as features of key frames. To evaluate the applicability of the proposed technique against various methods, the P(1) metric and the CC_WEB_VIDEO dataset are used. The experimental results show that the proposed method provides better performance and less processing time compared to the other methods.
- ESTIMATING TORSION OF DIGITAL CURVES USING 3D IMAGE ANALYSIS
Christoph Blankenburg, Christian Daul, Joachim Ohser
Curvature and torsion of three-dimensional curves are important quantities in fields like material science or biomedical engineering. Torsion has an exact definition in the continuous domain. However, in the discrete case most of the existing torsion evaluation methods lead to inaccurate values, especially for low resolution data. In this contribution we use the discrete points of space curves to determine the Fourier series coefficients which allow for representing the underlying continuous curve with Cesàro’s mean. This representation of the curve suits for the estimation of curvature and torsion values with their classical continuous definition. In comparison with the literature, one major advantage of this approach is that no a priori knowledge about the shape of the cyclic curve parts approximating the discrete curves is required. Synthetic data, i.e. curves with known curvature and torsion, are used to quantify the inherent algorithm accuracy for torsion and curvature estimation. The algorithm is also tested on tomographic data of fiber structures and open foams, where discrete curves are extracted from the pore spaces.
- FPGA IMPLEMENTATION OF ROAD NETWORK EXTRACTION USING MORPHOLOGICAL OPERATOR
Sujatha Chinnathevar, Selvathi Dharmar
In the remote sensing analysis, automatic extraction of road network from satellite or aerial images is the most needed approach for efficient road database creation, refinement, and updating. Mathematical morphology is a tool for extracting the features of an image that are useful in the representation and description of region shape. Morphological operator plays a significant role in the extraction of road network from satellite images. Most of the image processing algorithms need to handle large amounts of data, high repeatability, and general software is relatively slow to implement, so the system cannot achieve real-time requirements. In this paper, field programmable gate array (FPGA) architecture designed for automatic extraction of road centerline using morphological operator is proposed. Based on simulation and implementation, results are discussed in terms of register transfer level (RTL) design, FPGA editor and resource estimation. For synthesis and implementation of the above architecture, Spartan 3 XC3S400TQ144-4 device is used. The hardware implementation results are compared with software implementation results. The performance of proposed method is evaluated by comparing the results with ground truth road map as reference data and performance measures such as completeness, correctness and quality are calculated. In the software imple-mentation, the average value of completeness, correctness, and quality of various images are 90%, 96%, and 87% respectively. In the hardware implementation, the average value of completeness, correctness, and quality of various images are 87%, 94%, and 85% respectively. These measures prove that the proposed work yields road network very closer to reference road map.
- WAVELET ANALYSIS AND NEURAL NETWORK CLASSIFIERS TO DETECT MID-SAGITTAL SECTIONS FOR NUCHAL TRANSLUCENCY MEASUREMENT
Giuseppa Sciortino, Emanuela Orlandi, Cesare Valenti, Domenico Tegolo
We propose a methodology to support the physician in the automatic identification of mid-sagittal sections of the fetus in ultrasound videos acquired during the first trimester of pregnancy. A good mid-sagittal section is a key requirement to make the correct measurement of nuchal translucency which is one of the main marker for screening of chromosomal defects such as trisomy 13, 18 and 21. NT measurement is beyond the scope of this article. The proposed methodology is mainly based on wavelet analysis and neural network classifiers to detect the jawbone and on radial symmetry analysis to detect the choroid plexus. Those steps allow to identify the frames which represent correct mid-sagittal sections to be processed. The performance of the proposed methodology was analyzed on 3000 random frames uniformly extracted from 10 real clinical ultrasound videos. With respect to a ground-truth provided by an expert physician, we obtained a true positive, a true negative and a balanced accuracy equal to 87.26%, 94.98% and 91.12% respectively.
- AUTOMATIC RETINAL VESSEL DETECTION AND TORTUOSITY MEASUREMENT
Temitope Mapayi, Jules-Raymond Tapamo, Serestina Viriri, Adedayo Adio
As retinopathies continue to be major causes of visual loss and blindness worldwide, early detection and management of these diseases will help achieve significant reduction of blindness cases. However, an efficient automatic retinal vessel segmentation approach remains a challenge. Since efficient vessel network detection is a very important step needed in ophthalmology for reliable retinal vessel characterization, this paper presents study on the combination of difference image and K-means clustering for the segmentation of retinal vessels. Stationary points in the vessel center-lines are used to model the detection of twists in the vessel segments. The combination of arc-chord ratio with stationary points is used to compute tortuosity index. Experimental results show that the proposed K-means combined with difference image achieved a robust segmentation of retinal vessels. A maximum average accuracy of 0.9556 and a maximum average sensitivity of 0.7581 were achieved on DRIVE database while a maximum average accuracy of 0.9509 and a maximum average sensitivity of 0.7666 were achieved on STARE database. When compared with the previously proposed techniques on DRIVE and STARE databases, the proposed technique yields higher mean sensitivity and mean accuracy rates in the same range of very good specificity. In a related development, a non-normalized tortuosity index that combined distance metric and the vessel twist frequency proposed in this paper also achieved a strong correlation of 0.80 with the expert ground truth.