Gamma correction acceleration for real-time text extraction from complex colored images

Abstract

International audienceText extraction from complex colored images involves the suppression of unwanted background while keeping text features. Imaging devices are almost omnipresent and the unrestricted conditions of the images present new challenges for real-time OCR systems. The recently proposed Gamma Correction Method [1] is a robust and good quality method for text extraction in complex colored images. However it requires a large amount of computing resources and is not well suited for real-time applications. In this paper we propose an efficient acceleration of the GCM to drastically reduce its execution-time, while preserving the text extraction quality. Experimental results on ICDAR dataset show that our approach is effective and can reach a speedup of up to 11.430

An Efficient HW/SW Design for Text Extraction from Complex Color Image

“…3 presents the comparison of our HW/SW GCM design with works proposed in literature. All works use image from ICDAR dataset to evaluate their proposition, However, we can notice that our design is more performant and can consume less energy than [8] which proposes some optimization in the GCM method to determine the best gamma value from some modified image. This affects the efficiency of the text extraction.…”

“…Execution time (ms) Design specification [8] 478 ms Intel Core (TM) i3 @3.07 GHz [12] 702 s NIOS II + C. Instruction @100 MHz Our Design 890 ms ARM Cortex-A53 @667 MHz + GLCM coprocessor@100 MHz…”

“…These textural features are used to characterize each gamma modified image and extract text from image. Unfortunately, the GCM method provides a high computationally complexity which presents a big issue in computer vision specially for the applications that need a real-time text extraction [8] such as text-to-speech system for helping the blind persons. However, many works in literature are concentrated on accelerating the proceedings of the GCM method by using software (SW) optimization or/and hardware (HW) implementation.…”

“…However, many works in literature are concentrated on accelerating the proceedings of the GCM method by using software (SW) optimization or/and hardware (HW) implementation. Indeed, Kachouri et al [8] proposed an accelerated GCM (AGCM) which presents a software optimization of the GCM method. The AGCM proposes a sub-range of values where the chosen gamma should be found per the GCM method.…”

New Gamma Correction Method for real time image text extraction

“…In fact, for text extraction, the GCM [8] generates 100 modified images for each gamma value (the value of gamma can vary from 0.1 to 10.0 with increments of 0.1) from the original image. Then for each modified image, it generates the image threshold (1) using Otsu's method [10] and the Gray Level Co-occurence Matrix (GLCMs) [11] to calculate two texture features which are contrast (2) and energy (3). Then, it estimates the best gamma value from the contrast, the energy and the threshold of the image to generate the binarized and the corrected image.…”