Segmentation of Lip Print Images Using Clustering and Thresholding Techniques

Sandhya, Sankaran; Fernandes, Roshan; Sapna, S.; Rodrigues, Anisha P

doi:10.1007/978-981-15-3514-7_76

Cited by 5 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, the region-based approach applies clustering or thresholding techniques to separate between a lip and a background. Sandhya et al [14] applied Otsu's thresholding and K-means clustering from the grayscale lip-printed image. The separation of K-means clusters is based on Euclidean distance.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A lightweight deep learning approach to mouth segmentation in color images

Chotikkakamthorn

Ritthipravat²,

Kusakunniran³

et al. 2022

ACI

View full text Add to dashboard Cite

PurposeMouth segmentation is one of the challenging tasks of development in lip reading applications due to illumination, low chromatic contrast and complex mouth appearance. Recently, deep learning methods effectively solved mouth segmentation problems with state-of-the-art performances. This study presents a modified Mobile DeepLabV3 based technique with a comprehensive evaluation based on mouth datasets.Design/methodology/approachThis paper presents a novel approach to mouth segmentation by Mobile DeepLabV3 technique with integrating decode and auxiliary heads. Extensive data augmentation, online hard example mining (OHEM) and transfer learning have been applied. CelebAMask-HQ and the mouth dataset from 15 healthy subjects in the department of rehabilitation medicine, Ramathibodi hospital, are used in validation for mouth segmentation performance.FindingsExtensive data augmentation, OHEM and transfer learning had been performed in this study. This technique achieved better performance on CelebAMask-HQ than existing segmentation techniques with a mean Jaccard similarity coefficient (JSC), mean classification accuracy and mean Dice similarity coefficient (DSC) of 0.8640, 93.34% and 0.9267, respectively. This technique also achieved better performance on the mouth dataset with a mean JSC, mean classification accuracy and mean DSC of 0.8834, 94.87% and 0.9367, respectively. The proposed technique achieved inference time usage per image of 48.12 ms.Originality/valueThe modified Mobile DeepLabV3 technique was developed with extensive data augmentation, OHEM and transfer learning. This technique gained better mouth segmentation performance than existing techniques. This makes it suitable for implementation in further lip-reading applications.

show abstract

Section: Related Workmentioning

confidence: 99%

“…The lack of segmentation performance improvement factors leads to deteriorating segmentation accuracy. Moreover, Part A of LSN [4], LSFCNN [13], and U-net-based techniques [14,23,24] performed worst. They achieved the lowest segmentation accuracy compared to the other baselines, and Mobile DeepLabV3 [16,17].…”

Section: Acimentioning

confidence: 99%

A lightweight deep learning approach to mouth segmentation in color images

Chotikkakamthorn

Ritthipravat²,

Kusakunniran³

et al. 2022

ACI

View full text Add to dashboard Cite

show abstract

“…Lip prints can be recorded using various methods. Some of these methods include applying colouring agents like applying lipstick on the individual's lip and having them pressed on cellophane tape or a piece of paper [9]. Other methods of recording lip prints include using a finger printer, preferably a roller finger printer, applying conventional fingerprint developing powder or using magna brush with a magnetic powder [9].…”

Section: Introductionmentioning

confidence: 99%

“…Some of these methods include applying colouring agents like applying lipstick on the individual's lip and having them pressed on cellophane tape or a piece of paper [9]. Other methods of recording lip prints include using a finger printer, preferably a roller finger printer, applying conventional fingerprint developing powder or using magna brush with a magnetic powder [9]. One critical issue that should be noted from these methods is the fact that the lip prints are acquired using a contact‐based approach where it is disclosed on a durable surface.…”

Section: Introductionmentioning

confidence: 99%

“…One critical issue that should be noted from these methods is the fact that the lip prints are acquired using a contact‐based approach where it is disclosed on a durable surface. However, manual methods are mostly error prone [9]. Research that has been conducted on lip‐based identification thus far have used manual methods to acquire the lips, which were then digitised.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Lip print‐based identification using traditional and deep learning

Farrukh

Haar

2022

IET Biometrics

View full text Add to dashboard Cite

The concept of biometric identification is centred around the theory that every individual is unique and has distinct characteristics. Various metrics such as fingerprint, face, iris, or retina are adopted for this purpose. Nonetheless, new alternatives are needed to establish the identity of individuals on occasions where the above techniques are unavailable. One emerging method of human recognition is lip-based identification. It can be treated as a new kind of biometric measure. The patterns found on the human lip are permanent unless subjected to alternations or trauma. Therefore, lip prints can serve the purpose of confirming an individual's identity. The main objective of this work is to design experiments using computer vision methods that can recognise an individual solely based on their lip prints. This article compares traditional and deep learning computer vision methods and how they perform on a common dataset for lip-based identification. The first pipeline is a traditional method with Speeded Up Robust Features with either an SVM or K-NN machine learning classifier, which achieved an accuracy of 95.45% and 94.31%, respectively. A second pipeline compares the performance of the VGG16 and VGG19 deep learning architectures. This approach obtained an accuracy of 91.53% and 93.22%, respectively.

show abstract