Patel C.I.,Nirma University |
Garg S.,Nirma University |
Zaveri T.,Nirma University |
Banerjee A.,Dhirubhai Ambani Institute of ICT |
Patel R.,BVM Engineering College
Computers and Electrical Engineering | Year: 2016
Effective modeling of the human action using different features is a critical task for human action recognition; hence, the fusion of features concept has been used in our proposed work. By fusing several modalities, features, or classifier decision scores, we present six different fusion models inspired by the early fusion schemes, late fusion schemes, and intermediate fusion schemes. In the first two models, we have utilized early fusion technique. The third and fourth models exploit intermediate fusion techniques. In the fourth model, we confront a kernel-based fusion scheme, which takes advantage of kernel basis of classifiers i.e. Support Vector Machine (SVM). In the fifth and sixth models, we have demonstrated late fusion techniques. The performance of all models is evaluated with ASLAN and UCF11 benchmark dataset of action videos. We obtained significant improvements with the proposed fusion schemes relative to the usual fusion schemes relative state-of-the-art methods. © 2016.
Prajapati G.I.,SVMIT Engineering College |
Patel N.M.,BVM Engineering College
ICIIP 2011 - Proceedings: 2011 International Conference on Image Information Processing | Year: 2011
Lip detection from human front facial image belongs to image segmentation and an essential in many multimedia systems and real time applications such as videoconferencing, speech reading and understanding, face synthesis and facial animation through pronunciations. An efficient and effective detection of the lip contours from the human front facial image is relatively a difficult job in the field of computer vision and image processing due to the variation amongst human faces, lighting conditions and image acquisition conditions. In this paper, Three Phase Method (3PM) for lip detection and tracking from human front facial images is proposed and implemented. In the first phase of this method, the relevant and useful information is retrieved for mouth region from the given front facial image of human being. The second phase deals with detection and tracking of outer and inner lip contours. And the last phase concerns with combining the results of first and second phase of 3PM and findings of extreme control points of lip contours. The driving force behind this proposed method for lip detection and tracking is Snake's method along with image segmentation using RGB colour model and edge detection as the additional forces. The Proposed 3PM gives promising results but still with little inaccuracy in the results of moustache and with images with colour inequality in mouth region and poor illumination effects. © 2011 IEEE.
Kher R.,H+ Technology |
Pawar T.,BVM Engineering College |
Thakar V.,A D Patel Institute of Technology
WSEAS Transactions on Signal Processing | Year: 2014
The use of wearable ECG recorders is becoming common nowadays for the people suffering from cardiac disorders. Although it is a convenient option for hospitalization, it has an inherent drawback of recorded ECG being contaminated by motion artifacts due to various body movement activities of the wearer. In this paper, the spectral characteristics of motion artifacts occurring in wearable ECG (W-ECG) signals have been studied using principal component analysis (PCA) and wavelet transform. The residuals of PCA and wavelet transform characterize the spectral behaviour of the motion artifacts occurring in W-ECG signals. The ECG signals have been acquired from Biopac MP-36 system and a self-developed wearable ECG recorder. The performance is evaluated by power spectral density (PSD) plots of PCA residual errors as well as statistical parameters like mean, median and variance of PCA and wavelet residuals. The PSD plots indicate that the peak frequency of the motion artifacts occurring due to various body movements (like left arm up-down, right arm up-down, left and right legs up-down, waist twist, walking and sitting up-down) is located around 5-15 Hz, coinciding with the ECG spectrum.
Kher R.,H+ Technology |
Pawar T.,BVM Engineering College |
Thakar V.,A D Patel Institute of Technology
Proceedings of the 2013 6th International Conference on Biomedical Engineering and Informatics, BMEI 2013 | Year: 2013
Wearable ambulatory ECG (A-ECG) signals obtained using wearable ECG recorders inherently contain the motion artifacts due to various body movements of the subject. Classification of four such body movement activities (BMA) - left arm up-down, right arm up-down, waist twisting and walking-of five healthy subjects has been performed using artificial neural networks (ANN). The accelerometer data and the Gabor energy feature vectors have been combined to train the ANN. The overall BMA classification accuracy achieved by the ANN classifier is over 95%. © 2013 IEEE.
Patel R.,Bvm Engineering College |
Parmar S.,H+ Technology
Proceedings on 2014 2nd International Conference on "Emerging Technology Trends in Electronics, Communication and Networking", ET2ECN 2014 | Year: 2015
Content based image retrieval is used as an important tool by a radiologist, as it is very useful to diagnosis a patient. A set of interested images are retrieved from a large database, which helps to narrow down the problem under examination. Database consisting various images of organs like brain, lungs, neck, and colon. Haar like features are extracted and supplied to Support Vector Machine classifier, to decide that image belongs to which organ of a body. Once, it has been classified, process enters in a next phase of retrieval. In the phase of retrieval, where two different approaches are used for feature extraction, one based on intensity and other based on Statistical moments. Images are retrieved using a similarity measure for both approaches and a comparative analysis is shown in this paper. © 2014 IEEE.
Jaliya U.K.,Gujarat University |
Jaliya U.K.,BVM Engineering College |
Rathod J.M.,BVM Engineering College
Advances in Intelligent Systems and Computing | Year: 2015
Human Face recognition is one of the widely used biometric techniques for face identification and verification. It includes several subproblems like illumination variation, expression changes, aging, occlusion, and rotation of face images. Varying illumination is one of the well-known and challenging problems in human face recognition applications. In this paper, we proposed a novel approach to solve varying illumination problems in face images. The different stages include adaptive histogram equalization (AHE), Gaussian filtering, Log transform, difference of AHE+Gaussian filtering+Log image, and AHE+Log image, and then, we perform normalization. We are using principle component analysis (PCA) method for face recognition. The experimental results of proposed approach are compared with existing approaches, and it shows that our approach improves the performance of recognition under varying illumination conditions on Yale Face Database B. © 2015, Springer India.
Thakor D.,BVM Engineering College |
Shah A.,H+ Technology
Proceedings of the 2011 World Congress on Information and Communication Technologies, WICT 2011 | Year: 2011
A scheduling algorithm decides a schedule for a set of tasks. There are numbers of algorithm for scheduling tasks on a processor. Some of these algorithms are used for scheduling tasks on multiprocessor system either under the partitioning scheme or under the global scheduling scheme. The most common scheduling algorithms are: Earliest Deadline First (EDF) and Least Laxity First (LLF). They are optimal scheduling algorithms for single processor system, but problem arises when algorithms are used for multiprocessor system. In this paper, we have proposed a new algorithm, D-EDF. D-EDF scheduling algorithm overcomes the limitations of dynamic algorithm during overloaded conditions. The proposed algorithm D-EDF, simulated and tested for independent, preemptive, periodic tasks on tightly coupled real-time multiprocessor system under global scheduling. The performance is measured in terms of Success Ratio and Effective CPU Utilization. From experiments and result analysis it concludes that the proposed algorithm is very efficient in both underloaded and overloaded conditions. It performs always better than conventional EDF algorithm. The algorithm proposed in the paper performs quite well during overloaded conditions. © 2011 IEEE.
Patel N.,BVM Engineering College |
Signal, Image and Video Processing | Year: 2013
With better understanding of face anatomy and technical advances in computer graphics, 3D face synthesis has become one of the most active research fields for many human-machine applications, ranging from immersive telecommunication to the video games industry. In this paper we proposed a method that automatically extracts features like eyes, mouth, eyebrows and nose from the given frontal face image. Then a generic 3D face model is superimposed onto the face in accordance with the extracted facial features in order to fit the input face image by transforming the vertex topology of the generic face model. The 3D-specific face can finally be synthesized by texturing the individualized face model. Once the model is ready six basic facial expressions are generated with the help of MPEG-4 facial animation parameters. To generate transitions between these facial expressions we use 3D shape morphing between the corresponding face models and blend the corresponding textures. Novelty of our method is automatic generation of 3D model and synthesis face with different expressions from frontal neutral face image. Our method has the advantage that it is fully automatic, robust, fast and can generate various views of face by rotation of 3D model. It can be used in a variety of applications for which the accuracy of depth is not critical such as games, avatars, face recognition. We have tested and evaluated our system using standard database namely, BU-3DFE. © 2011 Springer-Verlag London Limited.
Patel D.,BVM Engineering College |
Jivani R.G.,BVM Engineering College
Journal of Engineering Science and Technology Review | Year: 2014
The main purpose of this review paper is to check whether quality lies within desired tolerance level which can be accepted by the customers. So, experimental investigation surface roughness and cutting force using various CNC machining parameters including spindle speed (N), feed rate (f), and depth of cut (d),flow rate (Q) and insert nose radius (r). As such, a solemn attempt is made in this paper to investigate the response parameters, viz., Cutting force and Surface Roughness (Ra) a by experimentation on EN 19 turning process. The Design of experiments is carried-out considering Taguchi Technique with four input parameters, namely, spindle speed, feed rate, and depth of cut, flow rate and insert nose radius .The experiments are conducted considering the above materials for L16 and then the impact of each parameter is estimated by ANOAVA. Then the regression analysis is carried-out to find the trend of the response of each material. This experimental study aims at taguchi method has been applied for finding the effect on surface roughness and cutting force by various process parameters. And after that we can easily find out that which parameter will be more affect. © 2014 Kavala Institute of Technology.
Pamnani Nanak J.,H.B. Patel Polytechnic |
Verma A.K.,Bvm Engineering College |
Bhatt Darshana R.,Bvm Engineering College
Journal of Engineering and Applied Sciences | Year: 2014
Self-Compacting Concrete (SCC) is highly workable concrete with high strength and high performance that can flow under its own weight through restricted sections without segregation and bleeding. SCC is achieved by reducing the volume ratio of aggregate to cementitious materials, increasing the paste volume and using various viscosity enhancing admixtures and superplasticizers. It is observed that the behaviour of the design concrete mix is significantly affected by variation in humidity and temperature both in fresh and hardened state. In this study, effect of 5 water-based curing techniques on compressive strength of M30 grade Self-Compacting Concrete (SCC) is discussed. It is observed that immersion method for curing gives maximum compressive strength while the lowest compressive strength is for ice curing. Hot water and sea water give 2nd highest strength at 28 days. It is concluded that, although pond immersion method is best for curing in extreme weather conditions SCC can prove effective for hot weather and sea water conditions. Wet covering method is quite effective giving about 92% strength than that of strength received from immersion method. In cold weather compressive strength gain is quite less about 82%. © Medwell Journals, 2014.