The problem of load estimation from sensor signals holds significance in the field of intelligent manufacturing. The goal of this work is to estimate the axial and spindle load values in a Computer Numerical Control machine from input sensor readings like spindle speed, feed rate, tool positions' etc. This can be viewed as a standard regression problem. Here, we propose a novel deep learning based regression technique that incorporates regression within the stacked autoencoder framework. Unlike the popular heuristic pretraining, fine-tuning approach, we solve all the parameters of the problem jointly. A variable splitting Augmented Lagrangian approach is employed to solve the ensuing optimization problem. Comparisons on standard regression models like linear, Least Absolute Shrinkage and Selection Operator (LASSO), Support Vector Regression and the traditional stacked autoencoder have shown that our technique considerably outperforms them.

We propose an action recognition technique using the 3D skeleton model of human without compromising the identity of the person. The skeleton model is defined as a set of 3D joint (e.g. knee or hip joint) coordinates obtained from the Kinect. The low frequency sensor noise in estimating the joint coordinates is removed after modeling the covariance matrix of the joint coordinates as a function of variance of individual joint coordinates. We determine a range for the threshold of this covariance matrix to detect active joints defining an action. Since, a sparse set of active joint coordinates is enough to represent an action, we map these coordinates to lower dimensional linear manifold before training using an SVM classifier. The recognition rate using our proposed approach outperforms competing approaches by at least 2%.

Developing analytical applications for IoT based on sensor signal processing tends to be complicated as applications are executed as sequence of steps comprising of multiple alternative algorithms, including suitable feature extraction modules depending on the goal of the application. Experience shows that developers spend considerable time and effort in performing feature extraction and dimensionality reduction. In this paper we propose a framework based on a relevant case study which allows developers to drag and drop algorithms to create a workflow chain, automatically select the most relevant signal features for the particular analytic application using a training data set to generate a model and deploy the model for use. The method reduces the effort and cost of development which is deemed highly important for the analytics industry.

In this paper authors have proposed a person identification method independent of his position with respect to the input sensor. The proposed method works for various postures or states namely, standing, sitting, walking. This method initially identifies the person's state and separate SVM based models are used for person identification (PI) for each of these three above mentioned states.

Many algorithms are now available for doing the same task (e.g. binarization, page segmentation, character recognition, etc.) in document image analysis (DIA) and choosing a particular algorithm(s) for a particular task is often a non-trivial problem. This paper proposes a model for automatically selecting the correct algorithm(s) for a given problem. Binarization has been taken a reference to illustrate the proposed approach. Several previously unexplored issues are addressed in this work. For example, only one method may not be good for the binarization of an entire document whereas a particular method may produce desired result for a particular region. Therefore, for a given document image, our model selects a set of one or more binarization techniques suitable for different regions of the document. This selection is completely automatic and guided by the machine learning approaches. Formulation of a completely automatic way for generating the annotated data for training the learning algorithms is also a novel contribution of this work. Evaluation of the approach is done using ICDAR 2003 Robust Reading data set and results highlight the potential of the proposed approach for automatic selection of correct DIA algorithm(s) from a set of several alternatives.

An embedded solution for automatic detection of Vehicle Identification Numbers (VIN) captured by a mobile camera has a number of real world applications. But the performance of available open source Optical Character Recognition (OCR) systems on VIN images captured by mobile phones is extremely poor because of the image quality affected by various noises. In a recent study of such images, we have observed that the performance of existing open source OCR systems can be improved by applying several image enhancement techniques on these images before sending them to the OCR engine. In this article, we have presented such a method that improves the recognition accuracy from 5.89% up to 82.3%.

Growing popularity of the connected TV i.e. the TV with Internet, leads to research on providing different value added services like web-TV mash-up to the user. It is very easy to get the textual context from a digital TV broadcast. But in developing countries like India still nearly 90% TV viewers are using analog Radio Frequency (RF) cable as the input TV signal and thus that textual information are difficult to obtain. This paper presents a light weight Video Optical Character Recognition (VOCR) system that can recognize the English texts from Indian TV videos with average 76.53% accuracy which is significantly higher than the 68.18% accuracy of Tesseract on the same set of videos. Moreover the proposed method is significantly less resource intensive compared to Tesseract so that the proposed method can be realized on any embedded platform.

A lot of research is now going on to extract the context of the show to provide additional information related to the TV show. One major method to extract the context from TV is to recognize the texts from the videos which is also known as video Optical Character Recognition (VOCR). The problem of VOCR from the TV shows of a multiligual country like India is more difficult. In India still more than 90% TV viewers are using RF Cable as input to TV and nearly 90% channels have multilingual texts in the TV shows. Thus the video quality is poor in compare to the modern digital TV signals as well as different text scripts are present in a single video frame. These made the problem of Indian TV context recognition more challenging. So this paper is concerned about the construction of a video corpus of text rich Indian TV shows. The proposed database contains more than 100 videos each of nearly 10 min duration containing text in the video frame. A statistical analysis of the corpus is also presented in the paper which can be used to identify the genre of TV show. The analysis also revealed that distribution of numerals, special characters, uppercase and lower case character can be used to classify a news video frame. This corpus is useful for a wide variety of research problems namely, (i) localization of the text regions from a video frame, (ii) recognition of texts from a video frame, (iii) extraction of context from video, and (iv) performance evaluation of a video OCR system.

Though designing of classifies for Indic script handwriting recognition has been researched with enough attention, use of language model has so far received little exposure. This paper attempts to develop a weighted finite-state transducer (WFST) based language model for improving the current recognition accuracy. Both the recognition hypothesis (i.e. the segmentation lattice) and the lexicon are modeled as two WFSTs. Concatenation of these two FSTs accept a valid word(s) which is (are) present in the recognition lattice. A third FST called error FST is also introduced to retrieve certain words which were missing in the previous concatenation operation. The proposed model has been tested for online Bangla handwriting recognition though the underlying principle can equally be applied for recognition of offline or printed words. Experiment on a part of ISI-Bangla handwriting database shows that while the present classifiers (without using any language model) can recognize about 73% word, use of recognition and lexicon FSTs improve this result by about 9% giving an average word-level accuracy of 82%. Introduction of error FST further improves this accuracy to 93%. This remarkable improvement in word recognition accuracy by using FST-based language model would serve as a significant revelation for the research in handwriting recognition, in general and Indic script handwriting recognition, in particular.

In this paper authors have proposed a multifactor based approach to automatically detect video shot boundaries. The compressed domain features of H.264 are used to assign the factor values. The features used in our approach are (i) Number of I Macroblocks (MBs) in a P frame, (ii) DC component of integer transformed luma coefficients and (iii) Number of MBs coded as P_Skip in P frame. A confidence score for all frames are assigned based on those above mentioned features. Experimental results show that the proposed approach can detect the shot boundaries successfully in real time. The system on different type of videos gives a recall rate of 0.98 and a precision rate of 0.94.

In this paper authors have proposed a multifactor based approach to automatically detect video shot boundaries. The compressed domain features of H.264 are used to assign the factor values. The features used in our approach are (i) Number of I Macroblocks (MBs) in a P frame, (ii) DC component of integer transformed luma coefficients and (iii) Number of MBs coded as P_Skip in P frame. A confidence score for all frames are assigned based on those above mentioned features. Experimental results show that the proposed approach can detect the shot boundaries successfully in real time. The system on different type of videos gives a recall rate of 0.98 and a precision rate of 0.94.

The Connected TV can be described as an Internet enabled TV. In the current paper we have proposed a system for connected TV that mash up the information from internet and RSS feeds related to the breaking news aired over the TV. The proposed system initially localize the text regions from the streamed video in hybrid mode, then recognize them and spot the key words and finally fetch the related information from Internet. Our experimental results show that the localization of the text regions from the video can work with no misses but have some false positives which are taken care by data semantic analysis. The errors of the Optical Character recognition (OCR) module are taken care by using string comparing techniques like longest common subsequence matching and Leveinsthein distance while matching with the RSS feed or internet.

This paper describes a practical and reliable solution/approach to achieve a semi-automated sewer pipeline inspection. The central goal of this work is to detect faults in the sewer lines which are a potential threat for underground drainage system. The major challenge for sewer line inspection is the classification and interpretation of the image data that are captured mainly by CCTV cameras mounted on robots. In this paper we had focused on providing the human operators a tool based on image processing technology that will help them to take decision on the pipe quality. The approach in this paper involves segmentation of the sewerage images based on prior knowledge of the defects. In this paper, a multi-factorial based approach has been proposed where the decision taking process involves a fuzzy mechanism based on weighted values of different parameters.