Abstract—Texts in characteristic scene pictures convey rich semantic data, which might be utilized to help an extensive variety of provisions, for example, object distinguishment, picture recovery, and human machine cooperation. Text in many pictures taken commonly by a cell phone can have a critical relative or point of view twisting, making the current content location and the consequent OCR motors inclined to disappointments. Not at all like other content recognition approaches that for the most part depend on either content structure or color, we propose an edge work that joins together both by overseeing content situated shade diminishment process with adjusted SWT data. SWT pixels mapped to shade space vote for the color they compare to. Shades accepting high SWT vote in all probability fit in with content zones and are obstructed from being mean-moved away and than applying composition invariant low rank convert that can identify and correct messages in self-assertive introductions in the picture against complex foundations, so that the writings could be accurately perceived by basic OCR motors.

Index Terms—Keywords: Natural scene pictures, SWT, Color decrease, Texture invariant low rank transform, Arbitrary introduction

Cite: Bhagyalaxmi P T and Bhaskar B, "COLOR HISTOGRAM BASED TEXT DETECTION IN IMAGES," International Journal of Electrical and Electronic Engineering & Telecommunications, Vol. 3, No. 3, pp. 96-101, July 2014.