融合图像灰度比值的离焦图像自动判别分离方法  

Automatic Discrimination and Separation Method for Defocused Images Based on Image Gray Ratio

作　　者：余海洋 范之国[1] 金海红[1,2] 彭瑾 Yu Haiyang;Fan Zhiguo;Jin Haihong;Peng Jin(School of Computer and Information,Hefei University of Technology,Hefei 230601,Anhui,China;School of Electronics and Information Engineering,Anhui Jianzhu University,Hefei 230601,Anhui,China)

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230601 [2]安徽建筑大学电子与信息工程学院,安徽合肥230601

出　　处：《激光与光电子学进展》2023年第22期59-69,共11页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61571177);安徽省高等学校自然科学研究项目(KJ2018JD12)。

摘　　要：利用图像离焦线索生成对应深度图像的方法因其快速、方便目前被广泛使用,但是离焦图像在离焦程度过高或过低时通常会丢失图像的深度信息,导致生成的深度图像不符合实际使用要求,因此需要对这些图像进行判别分离,但现有方法对不同场景的离焦图像模糊程度判别精度不足,缺乏统一标准,无法有效对离焦图像进行判别分离处理。针对此问题,提出一种融合图像灰度比值的离焦图像自动判别方法,首先,通过分析并利用离焦图像不同区域的梯度特征、频域特征,对图像模糊区域和清晰区域进行有效区分。其次,融合上述特征图像获取融合图像,因离焦图像的模糊区域和清晰区域离焦程度相差较大,表现在融合图像中两部分灰度值对比明显,因此利用融合图像两部分灰度平均值的比值作为判断离焦程度的衡量标准,当离焦图像该比值超出设定的阈值标准时,则认为该图像不满足深度图像生成条件,该图像将自动进行分离。最后,对比现有清晰度评价函数与本文方法对相同场景与不同场景、不同离焦模糊图像进行模糊程度的判别结果,发现所提方法可以较为准确快速地判别相同及不同场景下离焦图像模糊程度,有效分离不符合条件的离焦图像,提高深度图像的生成效率。Image defocus clues are widely used for generating corresponding depth images because of their speed and convenience.However,when the defocus degree of the defocused image is exceptionally high or low,the depth information of the image is often lost,making the generated depth images unable to satisfy the actual user requirements.It is necessary to distinguish and separate these images.However,existing methods are not sufficiently accurate for distinguishing the blur degree of the defocused images in different scenes,and lack the unified standards.Hence,they cannot distinguish and separate the defocused image effectively.In this study,an automatic discrimination method for the defocused image based on the image gray ratio is proposed to solve this problem.First,by analyzing and using the gradient and frequency-domain features of different regions of the out-of-focus image,it can effectively distinguish the blurred and clear areas of the image.Second,the feature images are fused to obtain a fusion image.Because the defocus degrees of the blurred and clear regions of the out-of-focus image are somewhat different,the contrast between the gray values of the two parts in the fusion image is evident.The ratio is used as a criterion to assess the degree of defocusing.When the ratio of the defocused image exceeds the set threshold standard,the image does not satisfy the depth image generation conditions,and separation is performed automatically.Finally,by comparing the existing definition evaluation function with the results obtained using the proposed method for discriminating the degrees of blurring of different defocused blurred images in the same and different scenes,the proposed method can more accurately and rapidly distinguish the degrees of blurring of defocused images in the same and different scenes,effectively separate the unqualified defocused images,and improve the generation efficiency of depth images.

关 键 词：图像处理 特征提取 离焦模糊检测 自动判断 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]