Non-text Classification Research Articles

A recurrent neural network based deep learning model for text and non-text stroke classification in online handwritten Devanagari document

A recurrent neural network based deep learning model for text and non-text stroke classification in online handwritten Devanagari document

Application of texture-based features for text non-text classification in printed document images with novel feature selection algorithm

Application of texture-based features for text non-text classification in printed document images with novel feature selection algorithm

Coalition game based feature selection for text non-text separation in handwritten documents using LBP based features

Text non-text classification is an important research problem in the domain of document image processing. Undesirably, this is an almost ignored research topic, particularly, when we consider the unconstrained offline handwritten document images. For text non-text classification, many times researchers employ high dimensional feature vectors, which not only increase the computation time and storage requirement, but also reduce the classification accuracy due to the presence of redundant or irrelevant features. Here lies the application of some feature selection (FS) algorithms in order to find out the relevant subset of the features from the original feature vector. In this paper, our aim is two-fold. Firstly, application of coalition game based FS technique to find out an optimal feature subset for classifying the components present in a handwritten document image either as text or non-text. Secondly, five variants of a popular texture based feature descriptor, called Local Binary Pattern (LBP), along with its basic version are fed to the FS module for identifying the useful patterns only which can pinpoint the regions of an image as most informative in terms of the said classification task. To the best of our knowledge, the approach is completely novel where coalition game based FS technique is applied for locating the feature-rich regions to be used for text non-text classification. For experimentation, we have prepared an in-house dataset along with its ground truth information which consists of 104 handwritten engineering class notes as well as laboratory copies that include handwritten and printed texts, graphical components and tables etc. Experimental outcomes confirm that the proposed approach not only helps in reducing the feature dimension significantly but also increases the recognition ability of all six feature vectors.

Probabilistic homogeneity for document image segmentation

In this paper we propose a novel probabilistic framework for document segmentation exploiting human perceptual recognition of text regions from complicated layouts. In particular, we conceptualize text homogeneity as the Gestalt pattern displayed in text regions, characterized by proximately and symmetrically arranged units with similar morphological and texture features. We model this pattern in the local region of a connected component (CC) using an hierarchical formulation, which simulates a random walk-and-check on a graph encoding the neighborhood of the CC. The proposed formulation allows an effective computation of what we call the probabilistic local text homogeneity (PLTH) using a weighted summation of the weights of the graph, which are derived from a probabilistic description of the homogeneity between neighboring CCs and computed through Bayesian cue integration. The proposed PLTH enables a multi-aspect analysis, where various primitives such as geometrical configuration, morphological features, texture characterization and location priors are integrated in one computational probabilistic model. This enables an effective text and non-text classification of CCs preceding any grouping process, which is currently absent in document segmentation. Experimental results show that our segmentation method based on the proposed PLTH model improves upon the state-of-the-art.

Text non-text classification based on area occupancy of equidistant pixels

Text detection and localization from text embedded natural images is still considered as a challenging problem in complex imagery environment. Foreground object segmentation followed by classification is a popular approach for this task. Component level object classification in clutter environment is therefore an important sub-problem. Appropriate extraction of foreground objects leads to effective classification that may certainly increase the performance of text detection. In this paper, a novel feature vector is developed based on area occupancy profile of equidistant pixels is reported for text/non-text classification. The generated feature descriptors are script invariant and much effective in practical scenario. This proposed feature set is evaluated on our dataset using five different pattern classifiers and experimental result shows that the said feature set yields more than 86% classification accuracy irrespective of scripts.

AUTNT - A component level dataset for text non-text classification and benchmarking with novel script invariant feature descriptors and D-CNN

Automated scene text recognition from camera images is considered as a pioneer research area through last few decades. Classification of foreground object components from camera images is an essential step of Text Information Extraction (TIE). Text/Non-text separation from complex document images as well as unstructured natural images is still a challenging task. Although, some works have been reported in this direction, component level standard benchmark datasets for specifically text/non-text classification are not available. In this paper, a new multi-script dataset of text and non-text components have been reported along with multi-purpose ground truth annotations. A novel feature set is also designed on the basis of distance information of medial skeleton points to set benchmark performance on this dataset. Also, a Deep Convolution Neural Network (D-CNN) based automated feature extraction and classification framework is developed for benchmarking purpose. More insight is put forward by conducting separate assessment of current two benchmark methods on component images originated from documents and natural scenes. Experimental results show that classification accuracy is over 94.00% for medial skeleton based feature descriptors and over 96.00% for D-CNN framework on both types of sources, which is pretty impressive in practical scenario.

An approach based on classifier combination for online handwritten text and non-text classification in Devanagari script

In this article, a method of analysing features of elliptical regions and combining outcomes of classifiers using Dempster–Shafer Theory (DST) is presented to classify online handwritten text and non-text data of any online handwritten document in the most popular Indic script—Devanagari. Although a few works exist in this regard in different non-Indic scripts, to our knowledge, no study is available to classify handwritten text and non-text document in online mode in any Indic script. The present method uses various structural and directional features analysed in elliptical regions to extract feature values from strokes of text and non-text data. The features are then studied separately in classification platforms based on Support Vector Machine (SVM) and Hidden Markov Model (HMM). The probabilistic outcomes of these two classification platforms are then combined using DST to improve the system performance. The efficiency of the present system has been measured on a self-generated dataset and it provides promising result.

Multi-script text versus non-text classification of regions in scene images

Text versus non-text region classification is an essential but difficult step in scene-image analysis due to the considerable shape complexity of text and background patterns. There exists a high probability of confusion between background elements and letter parts. This paper proposes a feature-based classification of image blocks using the color autocorrelation histogram (CAH) and the scale-invariant feature transform (SIFT) algorithm, yielding a combined scale and color-invariant feature suitable for scene-text classification. For the evaluation, features were extracted from different color spaces, applying color-histogram autocorrelation. The color features are adjoined with a SIFT descriptor. Parameter tuning is performed and evaluated. For the classification, a standard nearest-neighbor (1NN) and a support-vector machine (SVM) were compared. The proposed method appears to perform robustly and is especially suitable for Asian scripts such as Kannada and Thai, where urban scene-text fonts are characterized by a high curvature and salient color variations.

An efficient, classification-based approach for grouping pen strokes into objects

Objects in freely drawn sketches often have no spatial or temporal separation, making object identification difficult. We present a two-step stroke-grouping algorithm that first classifies individual strokes according to the type of object to which they belong, and then groups strokes with like classifications into clusters representing individual objects. The first step facilitates clustering by naturally separating the strokes, and both steps fluidly integrate spatial and temporal information. Our single-stroke classifier has comparable accuracy to an existing state-of-the-art single-stroke classifier on text vs. non-text classification, and is significantly more efficient. Furthermore, our classifier is also suitable for applications with more than two classes of strokes. Our approach to grouping is unique in its formulation as an efficient classification task rather than, for example, an expensive search task. In experiments on several types of sketches, our grouping method performed accurately, correctly grouping up to 92% of the ink, with up to 79% of the shapes being perfectly clustered.

A Combined Algorithm for Layout Analysis of Arabic Document Images and Text Lines Extraction

Text and not -text segmentation and text line extraction from document images are the most challenging problems of information indexing of Arabic document images such as books, technical articles, business letters and faxes in order to successfully process them in systems such as OCR. Researches on Arabic language related to documents digitization have been focusing on word and handwriting recognition. Few approaches have been proposed for layout analysis for Arabic scanned/captured documents. In this paper we present a page segmentation method that deals with the complexity of the Arabic language characteristics and fonts using the combination between two algorithms. The first method is the Run length Smoothing. The second method is the Connected Component Labeling algorithm for text and non-text classification using SVM. The combination of the two methods is based on Anding and Oring operations between the outputs of the two methods based on certain conditions. Then, dynamic horizontal projection based on dynamic updating of the threshold to commensurate with the noise associated with different documents and in between text lines. The performance evaluation is performed using manually generated ground truth representations from a dataset of Arabic document images captured using cameras and a hardware built for this purpose. Evaluation and experimental results demonstrate that the proposed text extraction method is independent from different document size, text size, font, shape, and is robust to Arabic document segmentation and text lines extraction. General Terms Image processing, Pattern Recognition.

Grouping Strokes into Shapes in Hand-Drawn Diagrams

Objects in freely-drawn sketches often have no spatial or temporal separation, making object recognition difficult. We present a two-step stroke-grouping algorithm that first classifies individual strokes according to the type of object to which they belong, then groups strokes with like classifications into clusters representing individual objects. The first step facilitates clustering by naturally separating the strokes, and both steps fluidly integrate spatial and temporal information. Our approach to grouping is unique in its formulation as an efficient classification task rather than, for example, an expensive search task. Our single-stroke classifier performs at least as well as existing single-stroke classifiers on text vs. nontext classification, and we present the first three-way single-stroke classification results. Our stroke grouping results are the first reported of their kind; our grouping algorithm correctly groups between 86% and 91% of the ink in diagrams from two domains, with between 69% and 79% of shapes being perfectly clustered.