the proceedings contain 181 papers. the topics discussed include: facial expression recognition with LDPP & LTP using deep belief network;facial expression recognition using Bandlet transform and centre symmetric ...
ISBN:
(纸本)9781538630457
the proceedings contain 181 papers. the topics discussed include: facial expression recognition with LDPP & LTP using deep belief network;facial expression recognition using Bandlet transform and centre symmetric - local binary pattern singing voice synthesis system for Carnatic music;automated polyp classification of gastroenteric lesion in colonoscopy videos;enhancement of underwater images using white balancing and Rayleigh-stretching;adaptive Volterra modeling for nonlinear systems based on LMS variants;web-based innovators marketplace on data jackets as communication support system;a novel machine learning approach to detect phishing websites;correlation based evaluation for search tools;a novel method for direction and deformation independent iris localization;beamforming and combining in multi-user large MIMO systems;automatic key frame extraction from videos for efficient mouse pain scoring;exploring dynamic factor graphs for forecasting building electrical load;an efficient character segmentation approach for handwritten Hindi text;and 3D Smith-chart applications for passive negative resistance in RF and microwave circuits.
the aim of this research is to design an intelligent system that addresses the problem of real-time localization and navigation of visually impaired (VI) in an indoor environment using a monocular camera. Systems that...
详细信息
ISBN:
(纸本)9781538657485
the aim of this research is to design an intelligent system that addresses the problem of real-time localization and navigation of visually impaired (VI) in an indoor environment using a monocular camera. Systems that have been developed so far for the VI use either many cameras (stereo and monocular) integrated with other sensors or use very complex algorithms that are computationally expensive. In this research work, a computationally less expensive integrated system has been proposed to combine imaging geometry, Visual Odometry (VO), Object Detection (OD) along with Distance-Depth (D-D) estimation algorithms for precise navigation and localization by utilizing a single monocular camera as the only sensor. the developed algorithm is tested for both standard Karlsruhe and indoor environment recorded datasets. Tests have been carried out in real-time using a smartphone camera that captures image data of the environment as the person moves and is sent over Wi-Fi for further processing to the MATLAB software model running on an Intel i7 processor. the algorithm provides accurate results on real-time navigation in the environment with an audio feedback about the person's location. the trajectory of the navigation is expressed in an arbitrary scale. Object detection based localization is accurate. the D-D estimation provides distance and depth measurements up to an accuracy of 94-98%.
the proceedings contain 29 papers. the topics discussed include: concept of policy information decision method in the cloud type virtual policy based network management scheme for the specific domain;Mulesoft ? salesf...
ISBN:
(纸本)9781538678756
the proceedings contain 29 papers. the topics discussed include: concept of policy information decision method in the cloud type virtual policy based network management scheme for the specific domain;Mulesoft ? salesforce integration using batch processing;AC transmission signal neural circuit and the design of deep learning model;convolutional neural network models for scattering patternrecognition of scanning electron microscopy images;stubs and drivers generator for object-oriented program testing using sequence and class diagrams;stubs and drivers generator for object-oriented program testing using sequence and class diagrams;a multi-objective minimum matrix search algorithm applied to large-scale bi-objective TSP;end-to-end speech synthesis for Bangla with text normalization;and measurement of line-of-sight detection using pixel quantity variation and application for autism.
this book includes papers from the 5thinternationalconference on Robot Intelligence Technologyand Applications held at KAIST, Daejeon, Korea on December 1315, 2017. It covers the following areas: artificial intellig...
ISBN:
(纸本)9783319784519
this book includes papers from the 5thinternationalconference on Robot Intelligence Technologyand Applications held at KAIST, Daejeon, Korea on December 1315, 2017. It covers the following areas: artificial intelligence, autonomous robot navigation, intelligent robot system design, intelligent sensing and control, and machine vision. the topics included in this book are deep learning, deep neural networks, image understanding, natural language processing, speech/voice/text recognition, reasoning & inference, sensor integration/fusion/perception, multisensor data fusion, navigation/SLAM/localization, distributed intelligent algorithms and techniques, ubiquitous computing, digital creatures, intelligent agents, computer vision, virtual/augmented reality, surveillance, patternrecognition, gesture recognition, fingerprint recognition, animation and virtual characters, and emerging applications. this book is a valuable resource for robotics scientists, computer scientists, artificial intelligence researchers and professionals in universities, research institutes and laboratories.
the paper proposes an approach that finds the similarity between two songs. this song pattern similarity can is established by knowing the note structures and their fundamental frequencies of each note of the two song...
详细信息
ISBN:
(纸本)9781728106465
the paper proposes an approach that finds the similarity between two songs. this song pattern similarity can is established by knowing the note structures and their fundamental frequencies of each note of the two songs and then compute the Pearson's Correlation of Coefficient. If the value of Correlation of Coefficient is very near to 1, that indicates the two songs are very much similar, otherwise it indicates a certain percentage of similarity. To establish the work, consider some songs as the test data and find out the song pattern similarities among them. the main aim of this paper is that it can be used as the song pattern similarity matching of music in the field of patternrecognition. the primary aspect of this work is to find the efficiency of some statistical approaches like Pearson's Correlation Coefficient is used for the matching patterns of two different song structures of combination of frequencies of different note structures in the field of Computational Musicology.
Hand grip force and motion pattern classification using bio signal such as Electromyogram (EMG) has been very important in current studies. EMG based pattern classification has gain the utmost consideration especially...
详细信息
the biggest challenge faced by Face recognition is to extract important facial features efficiently. Existing methods like SIFT, Root SIFT perform quite accurately, but fail in real world applications that require rea...
详细信息
ISBN:
(纸本)9781351124140;9780815357605
the biggest challenge faced by Face recognition is to extract important facial features efficiently. Existing methods like SIFT, Root SIFT perform quite accurately, but fail in real world applications that require real-time processing. the ORB feature detector-descriptor performs quite well in this regard. We have modified the ORB feature detector to Root ORB and used it as a pre-processing step for a study of classification algorithms for face recognition. Our results show that the Root SIFT feature detector-descriptor performs only 6.25% to 12.5% as fast as the Root ORB detector-descriptor. We have chosen to work with detector-descriptors like ORB rather than using Neural Networks to extract facial features. Compute-intensive methods like Neural Networks require a lot of training data and computational time to obtain these features.
Face recognition is transforming the way people are interacting with machines. Earlier it was used in specific domains like law enforcement but with extensive research being done in this field, it is being extended to...
详细信息
ISBN:
(纸本)9781351124140;9780815357605
Face recognition is transforming the way people are interacting with machines. Earlier it was used in specific domains like law enforcement but with extensive research being done in this field, it is being extended to various applications like automatic face tagging in social media, surveillance systems in airports, theaters and so on. Local feature detection and description is gaining a lot of significance in the face recognition community. Extensive research on SURF and SIFT descriptors have found widespread application. Key points matched by SURF and triangulated using Delaunay Triangulation boosts the interest points detected. Other modern techniques like machine learning and deep learning require huge amount of training data and computational capabilities which sometime becomes a limitation of its usage. In contrast, hand-crafted models like SURF, SIFT overcomes the requirement of training data and computing power. the pipeline proposed in the paper reduces the average computational power and increases accuracy.
the objective of this paper is to develop a methodology for automatic recognition of antinuclear antibodies by human epithelial type 2 (HEp-2) cell indirect immunofluorescence (IIF) image analysis to diagnose connecti...
详细信息
ISBN:
(纸本)9781538637197
the objective of this paper is to develop a methodology for automatic recognition of antinuclear antibodies by human epithelial type 2 (HEp-2) cell indirect immunofluorescence (IIF) image analysis to diagnose connective tissue disease. It integrates judiciously the merits of a new supervised canonical correlation analysis, termed as CuRSaR, and the theory of rough hypercuboid approach. the proposed method efficiently combines the textural information of HEp-2 cells, derived from local binary patterns and its variants, by canonical correlation analysis, while significant and relevant features for HEp-2 cell classification are extracted using the rough hypercuboid approach. Finally, the support vector machine is used to recognize one of the known staining patterns in IIF images. the effectiveness of the proposed method, along with a comparison with related feature extraction and multimodal data integration methods, is demonstrated on a set of HEp-2 cell images.
the proceedings contain 49 papers. the topics discussed include: Eyegaze tracking in handheld devices;secured privacy data using multi key encryption in cloud storage;Divya-Dristi: a smartphone based campus navigation...
ISBN:
(纸本)9781538637197
the proceedings contain 49 papers. the topics discussed include: Eyegaze tracking in handheld devices;secured privacy data using multi key encryption in cloud storage;Divya-Dristi: a smartphone based campus navigation system for the visually impaired;energy load forecasting using deep learning approach - LSTM and GRU in spark cluster;a direction-based exponential mutation operator for real-coded genetic algorithm;CCA secure proxy re-encryption scheme for secure sharing of files through cloud storage;indoor localization for smart-handhelds with stable set of wireless access points;harvested profile aware multi hop routing protocol for wireless sensor network;segmentation of meaningful text-regions from camera captured document images;DETSApp: an app for disaster event tweets summarization using images posted on Twitter;efficient power extraction from SPV system in partially shaded condition: a comparative study between classical and fuzzy logic control;automatic text summarization using internal and external information;TR-LBP: a modified local binary pattern-based technique for 3D face recognition;real-time evaluation of an interval type-2 fuzzy PID controller on servo position control system;and cycle structure of non-uniform cellular automata.
暂无评论