Automatic burn area identification in color images

Badea, Mihai-Sorin; Vertan, Constantin; Florea, Corneliu; Florea, Laura; Bădoiu, Silviu Constantin

doi:10.1109/iccomm.2016.7528325

Cited by 20 publications

(16 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current state-of-the-art in the segmentation and classification of skin burn depth was using deep learned convolutional neural network (CNN) [4], [5] and fully convolutional network (FCN) [6] in identifying the burned skin from the healthy skin. However, deep learning requires [2] a large amount of labelled data and high computational power.…”

Section: Introductionmentioning

confidence: 99%

“…Badea et al [4] proposed two main approaches for the distinguishing of burns wounds which were identifying features that were capable of differentiating between healthy skin and the burn wound as well as being dependent on the feature selection performed by intelligent classifiers, such as deep learned convolutional neural network. Their approach is to identify the rectangular patches corresponding to burns.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Study of Segmentation Algorithms in the Classification of Human Skin Burn Depth

Kuan

Chua

Safawi

et al. 2020

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

A correct first assessment of a skin burn depth is essential as it determines a correct first burn treatment provided to the patients. The objective of this paper is to conduct a comparative study of the different segmentation algorithms for the classification of different burn depths. Eight different hybrid segmentation algorithms were studied on a skin burn dataset comprising skin burn images categorized into three burn classes by medical experts; superficial partial thickness burn (SPTB), deep partial thickness burn (DPTB) and full thickness burn (FTB). Different sequences of the algorithm were experimented as each algorithm was able to segment differently, leading to different segmentation in the final output. The performance of the segmentation algorithms was evaluated by calculating the number of correctly segmented images for each burn depth. The empirical results showed that the segmentation algorithm that was able to segment most of the burn depths had achieved 40.24%, 60.42% and 6.25% of correctly segmented image for SPTB, DPTB and FTB respectively. Most of the segmentation algorithms could not segment well for FTB images because of the different nature of the burn wounds as some of the FTB images contained dark brown and black colors. It can be concluded that a good segmentation algorithm is required to ensure that the representative features of each burn depth can be extracted to contribute to higher accuracy of classification of skin burn depth.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Segmentation Algorithms in the Classification of Human Skin Burn Depth

Kuan

Chua

Safawi

et al. 2020

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

show abstract

“…Burn injuries are severe problems for a human being. In the case of death from unintentional injury, burns represent the fourth leading cause [2].…”

Section: Introductionmentioning

confidence: 99%

“…The crucial part of this work is to label these images so that the proper treatment can be given. As specialist diagnoses for the proper treatment, in the same manner, the skin burn images are enhanced, and then images are labeled [2]. The primary objective of this work is to develop a classification system for burn injury images using color characteristics.…”

Section: Introductionmentioning

confidence: 99%

Feature Extraction Based Machine Learning for Human Burn Diagnosis From Burn Images

Yadav

Sharma

Singh

et al. 2019

IEEE J. Transl. Eng. Health Med.

View full text Add to dashboard Cite

Burn is one of the serious public health problems. Usually, burn diagnoses are based on expert medical and clinical experience and it is necessary to have a medical or clinical expert to conduct an examination in restorative clinics or at emergency rooms in hospitals. But sometimes a patient may have a burn where there is no specialized facility available, and in such a case a computerized automatic burn assessment tool may aid diagnosis. Burn area, depth, and location are the critical factors in determining the severity of burns. In this paper, a classification model to diagnose burns is presented using automated machine learning. The objective of the research is to develop the feature extraction model to classify the burn. The proposed method based on support vector machine (SVM) is evaluated on a standard data set of burns—BIP_US database. Training is performed by classifying images into two classes, i.e., those that need grafts and those that are non-graft. The 74 images of test data set are tested with the proposed SVM based method and according to the ground truth, the accuracy of 82.43% was achieved for the SVM based model, which was higher than the 79.73% achieved in past work using the multidimensional scaling analysis (MDS) approach.

show abstract

“…This work is motivated by the need for an effective automated skin burn depth classification as burn specialists and medical personnel are not always available on site during burn accidents. The current state-of-the-art in burn depth classification is performed by using deep learned convolutional neural network to identify features that are capable to differentiate between healthy skin and burn area [5]. The images used were captured using colour-thermal camera instead of digital camera and the images were manually registered with infrared markings.…”

Section: Introductionmentioning

confidence: 99%

Extracting Novel Features for Skin Burn Image Classification

Nei*,

Chua,

Safawi

et al. 2019

IJRTE

View full text Add to dashboard Cite

In this paper, the objective is to propose a set of novel features for the classification of different burn depths by using an image mining approach. Both colour and texture features were studied on skin burn dataset comprising skin burn images categorized into three burn depths by the burn specialist. The performance of the proposed feature set was evaluated using linear SVM on 10-fold cross validation method. The empirical results showed that the six proposed novel features, when used together with the common image features, was the best set of features that was able to classify most of the burn depths in terms of accuracy, precision and recall measures with the values of 96.8750%, 96.9697% and 96.6667% respectively. Automated classification of skin burn depths is essential because the initial burn treatment provided to patients are usually based on the first evaluation of the skin burn injuries by determining the burn depths. However, the burn specialist may not always be available at the accident site. In conclusion, the features extracted that represent the burn characteristics specifically in terms of colour and texture were able to effectively characterise the depth of burns in accordance to burn depth classification.

show abstract

Automatic burn area identification in color images

Cited by 20 publications

References 12 publications

A Comparative Study of Segmentation Algorithms in the Classification of Human Skin Burn Depth

A Comparative Study of Segmentation Algorithms in the Classification of Human Skin Burn Depth

Feature Extraction Based Machine Learning for Human Burn Diagnosis From Burn Images

Extracting Novel Features for Skin Burn Image Classification

Contact Info

Product

Resources

About