• Mandeep Kaur
• Dr. Sukhjeet Kaur

Image enhancement is an important step which is desirable as pre-processing step in number of applications i.e. object detection, segmentation, contrast improvement etc. Images captured i.e. SAR, Medical, natural images etc. are sometimes not clear due to noise in them, have unbalanced contrast caused by bad weather condition, low lightning, camera sensor defects etc. and need enhancement before further processing needed in segmentation, classification of images. Different types of methods have been proposed both in spatial and transform domain which are helpful in enhancement of images. Some methods which give effective results are contrast stretching, power-law or gamma correction, histogram equalization which comes in spatial domain category. In this work, a modified methods in these categories are analyzed and implemented which are effective than traditional techniques found in spatial domain. Total eight methods has been presented in which three methods are advancements in HE technique named as CLAHE, BBHE and DSIHE which preserves the contrast based on average mean and entropy value of the images. One method uses hybrid of HE and contrast-stretching first divided the input image into two halves based on mean average value. Two methods are based on gamma correction in which first method uses adaptive gamma correction along with weighting distribution. These methods can progressively increase the low intensity and avoid the significant decrement of the high intensity. Furthermore, the weighting distribution (WD) function is also applied to slightly modify the statistical histogram and lessen the generation of adverse effects. Effectiveness of the presented methods has been compared using seven different quality matrices named as MSE, PSNR, Contrast, gradient, entropy, NC and MSSIM in which four different datasets comprise of ten images each from natural scenes, medical ultrasound images, SAR and HDR are experimented. It has been found that optimal gamma correction and DSIHE methods balances the contrast than other methods in all type of images. Contrast-stretching gives effective results than the remaining methods when contrast parameter is considered. CLAHE gives effective results when gradient parameter is considered. For comparing NC values almost all methods are effective as all approaches to one but adaptive and optimal gamma correction along with contrast-stretching gives high value of NC parameter when all dataset are considered. Similarly adaptive and optimal gamma correction found effective when SAR and medical datasets are considered but for natural and HDR images optimal gamma correction and contrast-stretching found more effective than the rest.

Image Enhancement, Spatial Domain Techniques, evaluation parameters

"COMPARATIVE ANALYSIS OF VARIOUS SPATIAL DOMAIN METHODS FOR IMAGE ENHANCEMENT ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 9, page no.137-153, September-2018, Available :http://www.jetir.org/papers/JETIR1809327.pdf

"COMPARATIVE ANALYSIS OF VARIOUS SPATIAL DOMAIN METHODS FOR IMAGE ENHANCEMENT ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 9, page no. pp137-153, September-2018, Available at : http://www.jetir.org/papers/JETIR1809327.pdf