Image Processing Algorithm
JPEG to Binary Conversion
Mansi Gupta
Dept. of Computer Sc. &Engg.,Lingaya’s University,Faridabad, Haryana,India
manasigupta18@gmail.com,
Meha Garg
Dept. of Computer Sc. &Engg.,Lingaya’s University,Faridabad, Haryana,India
mehagarg.be@gmail.com
Prateek Dhawan
Dept. of Computer Sc. &Engg.,Lingaya’s University,Faridabad, Haryana,India
prateek.3212@gmail.com
Abstract –
The JPEG processing algorithm works beston photographs and paintings of realistic scenes withsmooth variations of tone and colour but is not wellsuited to files that will undergo multiple edits. Thedirect conversion of jpeg image into binary format isvery low in efficiency. In this paper, the process of conversion of jpeg image to binary image is beingdone in a step by step manner, without using directinbuilt function of jpeg to binary in MATLAB. As thebinary image is used for comparison purposes, the jpeg image is converted into LAB format to make theluminance scale perceptually more uniform, so thatthe procedure becomes more efficient.
Keywords:
LAB, Binary image, sign language
I.
INTRODUCTIONJPEG (named after the Joint Photographic ExpertsGroup who created the standard) is a commonlyused method of lossy compression for photographicimages. [1]Another format is the binary format which has pixels with only two possible intensity values.They are normally displayed as black and white. Numerically, the two values are often 0 for black,and either 1 or 255 for white.Binary images are often produced by thresholdinga grayscale or color image, in order to separate anobject in the image from the background. The color of the object (usually white) is referred to as theforeground color. The rest (usually black) isreferred to as the background color. However,depending on the image which is to be threshold,this polarity might be inverted, in which case theobject is displayed with 0 and the background iswith a non-zero value. [2]As for the LAB colour space, L* stands for luminance, a* is the red-green axis, and b* is the blue-yellow axis. The asterisks were added todifferentiate CIE from another L,a,b model.[3]Although CIE L*a*b* has a large color gamut andis considered as the most accurate colour model, itis often used as a reference only or as anintermediary for colour space conversion.II.
VARIOUS METHODS FOR COMPUTING BINARY IMAGEThe JPEG image can be converted into Binaryimage by writing codes using C# or Visual Basic.This conversion can also be implemented byconversion of RGB into grayscale first and theninto binary.It can also be done with the help of an inbuiltfunction in MATLAB. The function isim2bw(RGB, level). Applying this function on theimage for alphabet A generates a corresponding binary image in fig.1
Fig.1 JPEG and Binary image for alphabet A
III.
PROBLEM DEFINITIONThe object is hands of the sign language useer which must be in fully in black when displayed inthe binary image. The image in fig. 1 is not clear and has distortions too, i.e., the hand portion is notin black completely. This would hinder gaining
(IJCSIS) International Journal of Computer Science and Information Security,Vol. 8, No. 2, May 201075http://sites.google.com/site/ijcsis/ISSN 1947-5500