Adaptive image enhancement method using contrast limitation based on multiple layers BOHE

Pei, Tao; Pei, Yanliang; Celenk, Mehmet; Fu, Qiaoyan; Wu, Aibin

doi:10.1007/s12652-020-01810-9

Cited by 10 publications

(8 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Median filter noise removal algorithm is used to remove the noise 30 of the dental panoramic radiography. Since the structure of each tooth is different non‐linear filtering method is proposed in this work 31 .…”

Section: Proposed Methodologymentioning

confidence: 99%

Detection of periodontal bone loss in mandibular area from dental panoramic radiograph using image processing techniques

Vigil

Bharathi

2021

Concurrency and Computation

View full text Add to dashboard Cite

Medical imaging plays the vital role in diagnosis of abnormalities. Periodontitis is a common chronic inflammatory disease damaging the soft tissue that untreated can lead to loss of bone, which supports the teeth. The severity of periodontitis is correlated to pocket depth in alveolar area. Even if analyses of the pocket depth can be manually performed, an automatic assistive tool can drastically help radiologists conduct more accurate analyses. In the proposed research, image processing algorithms were developed to compute pocket depth and diagnose the periodontitis. Radiologists manually segmented 350 panoramic radiographic images, dividing them into normal and periodontitis. The same dataset is used in our work to validate the Classification algorithm. The images are preprocessed with median filter and histogram equalization to improve the contrast and then segmented using two‐dimensional‐Otsu thresholding method into teeth and bony area in the mandibular region. Normal pocket depth of 3 mm as reported by American Academy of Periodontology is equivalently converted to pixel height in the radiographic images. Based on this pocket depth rule based classification method classifies the images into normal and periodontitis. The proposed work achieved 91.34% accuracy, 92.8% sensitivity, and 95.47% F‐score in classifying the dental panoramic radiography.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Detection of periodontal bone loss in mandibular area from dental panoramic radiograph using image processing techniques

Vigil

Bharathi

2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…For example, an image of 640×480 image pixels must be equalized with a histogram 307200 times. The techniques under this sub-class include adaptive histogram equalization (AHE) [8], contrast-limited adaptive histogram equalization (CLAHE) [38], POSHE [39], cascaded multistep binomial filtering histogram equalization (CMBFHE) [40], adaptive image enhancement method using contrast limitation based on multiple layers (BOHE) [41], and iterated adaptive entropy clip limit histogram equalization (IAECHE) [5]. The AHE technique addresses the non-uniform illumination drawback of GHE by handling all image pixels and generates an image with homogenous brightness [8].…”

Section: E) Local Histogram Equalizationmentioning

confidence: 99%

“…The authors in [41] claimed that POSHE improves the local information and reduces image noise in multiple stages. POSHE applies fast BOHE to achieve multilayer improvements of different window sizes created by the original image.…”

Section: E) Local Histogram Equalizationmentioning

confidence: 99%

Adaptive Entropy Index Histogram Equalization for Poor Contrast Images

Majeed

Isa

2021

IEEE Access

View full text Add to dashboard Cite

“…For example, a 640 × 480 pixel image must be histogram equalized 307,200 times. Several techniques proposed for this category are adaptive histogram equalization (AHE) [10], contrast-limited adaptive histogram equalization (CLAHE) [15], partially over-loaded sub imaging histogram equalization (POSHE) [16], cascaded multistep binomial filtering histogram equalization (CMBFHE) [17], and adaptive image enhancement method using contrast limitation based on multiple layers (BOHE) [18]. AHE technique resolves the non-uniform illumination drawback of GHE by manipulating all image pixels and then generating a resultant image with homogeneous brightness.…”

Section: Introductionmentioning

confidence: 99%

“…POSHE has shown little improvement in computing time [16]. [18] authors claimed that the technique was developed to enhance local details and reduce noise by passing through different stages. This technique works in multi-layer enhancement by applying fast BOHE technique to different window sizes generated by the original image.…”

Section: Introductionmentioning

confidence: 99%

Iterated Adaptive Entropy-Clip Limit Histogram Equalization for Poor Contrast Images

Majeed

Isa

2020

IEEE Access

View full text Add to dashboard Cite

Poor contrast and hidden details in images owing to low camera quality, bad illumination, and poor setting for environment capture are the main challenges in the contrast enhancement process. Histogram equalization (HE) based methods are commonly used to reduce these problems. However, resultant images produced by existing methods often look unnatural, are affected by unwanted artifacts, and suffer from washedout effects. Therefore, this study proposes a local type of HE based contrast enhancement method called iterated adaptive entropy-clip limit histogram equalization (IAECHE). First, IAECHE divides the image into multiple sub-images to fine-tune the local details. Each sub-image will be applied with a different number of enhancement iterations, which are adaptively determined by IAECHE. This process ensures the best enhanced resultant sub-images, which are then merged to produce the final resultant image. A quantitative analysis of 820 images from three databases shows that IAECHE successfully produces better resultant images with better contrast, clearer details and less affected by noises. The proposed method also successfully preserves the details and structures of the images compared to several state-of-the-art methods. These findings are supported and validated by quantitative analysis. IAECHE produces high average values of peak signal-to-noise ratio, discrete entropy, absolute mean brightness error, structure similarity index, and contrast improvement index. From the analyses, the proposed IAECHE technique is proven to be capable of enhancing images' contrast, details, and structure. Thus, it has high potential for applications in the machine vision, industrial, and medical imaging fields. INDEX TERMSHistogram equalization-based method, Histogram entropy, Histogram clip limit, Histogram peak.

show abstract

Adaptive image enhancement method using contrast limitation based on multiple layers BOHE

Cited by 10 publications

References 29 publications

Detection of periodontal bone loss in mandibular area from dental panoramic radiograph using image processing techniques

Detection of periodontal bone loss in mandibular area from dental panoramic radiograph using image processing techniques

Adaptive Entropy Index Histogram Equalization for Poor Contrast Images

Iterated Adaptive Entropy-Clip Limit Histogram Equalization for Poor Contrast Images

Contact Info

Product

Resources

About