Dibyayan Chakraborty

OCR from Video Stream of Book Flipping

Optical Character Recognition (OCR) in video stream of flipping pages is a challenging task because flipping at random speed cause difficulties to identify frames that contain the open page image (OPI) for better readability. Also, low resolution, blurring effect shadows add significant noise in selection of proper frames for OCR. In this work, we focus on the problem of identifying the set of optimal representative frames for the OPI from a video stream of flipping pages and then perform OCR without using any explicit hardware. To the best of our knowledge this is the first work in this area. We present an algorithm that exploits cues from edge information of flipping pages. These cues, extracted from the region of interest (ROI) of the frame, determine the flipping or open state of a page. Then a SVM classifier is trained with the edge cue information for this determination. For each OPI we obtain a set of frames. Next we choose the central frame from that set of frames as the representative frame of the corresponding OPI and perform OCR. Experiments are performed on video documents recorded using a standard resolution camera to validate the frame selection algorithm and we have obtained 88% accuracy. Also, we have obtained character recognition accuracy of 82% and word recognition accuracy of 77% from such book flipping OCR.

Baseline detection of multi-lingual unconstrained handwritten text lines

A novel method for baseline detection of multi-lingual multi-oriented text lines.To our knowledge, this is the first baseline detection method for multi-turn text lines.The method uses machine learning along with rotation invariant features for constructing the baseline.The method improves the performance of the state-of-the-art character segmentation method substantially. Many handwritten text recognition systems use the baseline information for better recognition of text line characters. Improper baseline detection reduces the performance of the recognition. In this paper we propose a novel baseline detection scheme for unconstrained handwritten text lines of multilingual documents. For baseline detection of a text line, at first, we detect the set of significant contour points (S-points) of the text line. Every non-singleton subsets of S-points forms a curve. The orientation invariant features of the curve determine whether the curve can construct a probable baseline of the input text line or not. It is determined by an SVM, trained using the orientation invariant features of the curves. The curves classified as probable baselines, are sorted according to their relative positions in ascending order to get the optimal baseline. We tested our method on different handwritten text lines of Bangla(Bengali), English(Roman), Kannada, Oriya, Devnagari and Persian scripts and obtained encouraging results.

On a Special Class of Boxicity 2 Graphs

We define and study a class of graphs, called 2-stab interval graphs (2SIG), with boxicity 2 which properly contains the class of interval graphs. A 2SIG is an axes-parallel rectangle intersection graph where the rectangles have unit height (that is, length of the side parallel to Y-axis) and intersects either of the two fixed lines, parallel to the X-axis, distance 1 + e (0 < e < 1) apart. Intuitively, 2SIG is a graph obtained by putting some edges between two interval graphs in a particular rule. It turns out that for these kind of graphs, the chromatic number of any of its induced subgraphs is bounded by twice of its (induced subgraph) clique number. This shows that the graph, even though not perfect, is not very far from it. Then we prove similar results for some subclasses of 2SIG and provide efficient algorithm for finding their clique number. We provide a matrix characterization for a subclass of 2SIG graph.

Bottleneck bichromatic full Steiner trees

Abstract Given two sets of points in the plane, Q of n (terminal) points and S of m (Steiner) points, where each of Q and S contains bichromatic points (red and blue points), a full bichromatic Steiner tree is a Steiner tree in which all points of Q are leaves and each edge of the tree is bichromatic, i.e., connects a red and a blue point. In the bottleneck bichromatic full Steiner tree (BBFST) problem, the goal is to compute a bichromatic full Steiner tree T, such that the length of the longest edge in T is minimized. In the k-BBFST problem, the goal is to find a bichromatic full Steiner tree T with at most k ≤ m Steiner points from S, such that the length of the longest edge in T is minimized. In this paper, we first present an O ( ( n + m ) log ⁡ m ) time algorithm that solves the BBFST problem. Then, we show that k-BBFST problem is NP-hard and cannot be approximated within a factor of 5 in polynomial time, unless P = N P . Finally, we give a polynomial-time 9-approximation algorithm for the k-BBFST problem.

Frame selection for OCR from video stream of book flipping

Optical Character Recognition (OCR) in video stream of flipping pages is a challenging task because flipping at random speed causes difficulties in identifying the frames that contain the open page image (OPI). Also, low resolution, blurring effect, shadow, etc., add significant noise in selection of proper frames for OCR. In this paper, we focus on identifying a set of representative frames from the video stream of flipping pages without using any explicit hardware and then perform OCR on these frames for recognition. Thus, an end-to-end solution is proposed for video stream of flipping pages. To select an OPI, we present an efficient algorithm that exploits cues from edge information during flipping event. These cues, extracted from the region of interest (ROI) of the frame, determine the flipping or open state of a page. The open state classification is performed by an SVM classifier following training of the edge cue information. After selecting a set of frames for each OPI, a representative frame from OPI set is chosen for OCR. Experiments are performed on videos captured using standard resolution camera. We have obtained 88.81 % accuracy on representative frame selection from the proposed method whereas when compared with GIST (Oliva and Torralba, Int J Comput Vis 42(3):145–175 (2001)), the accuracy was only 51.28 %. To the best of our knowledge this is the first work in this area. After frame selection, we have achieved 83.31 % character recognition accuracy and 78.11 % word recognition accuracy with traditional OCR in our dataset of flipping book.

On Local Structures of Cubicity 2 Graphs

A 2-stab unit interval graph (2SUIG) is an axes-parallel unit square intersection graph where the unit squares intersect either of the two fixed lines parallel to the

Duplicate open page removal from video stream of book flipping

X

On bounds on bend number of split and cocomparability graphs.

-axis, distance

Approximating Minimum Dominating Set on String Graphs

1 + \epsilon

On bounds on bend number of classes of split and cocomparability graphs.

(