Using a Knowledge-Based Approach to Remove Blocking Artifacts in Skin Images for Forensic Analysis

Tang, Chaoying; Kong, Adams Wai-Kin; Craft, Noah

doi:10.1109/tifs.2011.2157821

Cited by 20 publications

(32 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed approach is knowledge-based (KB), which removes JPEG blocking artifacts and recovers skin features, The authors developed various algorithms: Markov-model-based algorithm is a faster one-pass algorithm to implement the inference, while block synthesis algorithm to handle the various cases where compressed blocks are not included in the training set. Tang et al [27] (2011). There is also an improvement in the visual quality of biometric features.…”

Section: International Journal Of Engineering and Advanced Technologymentioning

confidence: 99%

Forensic Science Research Summary for Forgery Detection of Digital Images

Monika¹,

Ece²,

Bansal³

et al. 2020

IJEAT

View full text Add to dashboard Cite

An important measure of proof collection, storage, and authentication in forensic sciences, which decide the safety and security of any system documents, which can be either portable document formats or scanned images. To gather evidence, or plan a forensic investigation digital images are secured with different modern methodologies. Digital image analysis includes image recovery and surveillance for image information improvement. The goal of forgery detection is to maximize the extraction of information from manipulated images, particularly noisy and post-processed images. Because digital image processing is becoming popular with many advantages in scientific and engineering applications, the forgery techniques are also growing at a rapid rate. Therefore, the main focus is on different types of forgery detection in digital image processing with the help of all transform techniques and comparing their best results for further improvement in order to generate a new approach for a future forensic science investigation.

show abstract

Section: International Journal Of Engineering and Advanced Technologymentioning

confidence: 99%

Forensic Science Research Summary for Forgery Detection of Digital Images

Monika¹,

Ece²,

Bansal³

et al. 2020

IJEAT

View full text Add to dashboard Cite

show abstract

“…Finally we entail our KB to learn a new clause using the method of resolutions. [5,9] To effectively design knowledge framework for a large number of ICD-10 codes we will use Conceptual Graph (CG) way of representation.…”

Section: Proposed Systemmentioning

confidence: 99%

“…Penumococcal, Streptococcal, Staphylococcal and other bacterial meningitis are defined and assigned a corresponding ICD-10 code is assigned to it. [9] Further again the various causes for which bacterial part is caused is also taken into consideration. At last the unspecified part of meningitis is also taken into consideration and corresponding ICD code is given to it.…”

Section: Introductionmentioning

confidence: 99%

Designing knowledge representation framework for ICD-10

Kharadkar

Selwyn

2015

2015 International Conference on Futuristic Trends on Computational Analysis and Knowledge Management (ABLAZE)

View full text Add to dashboard Cite

Knowledge Representation (KR) is the field related Artificial Intelligence which basically deals with the usage of formal symbols which are used to represent a collection of proposition believed by putative agents. In KR we deal with two types of representations Symbol and Concept level representations. ICD-10 is the 10th revision of the International Statistical Classification of Diseases and Health related problems. Its primary job is to code for diseases, symptoms, complaints and external causes of injury. It uses a 7-bit code to represent all diseases. The main focus of our research work is that we are going to represent the 7 bit code into a logical unit and logical entailments to form conceptual relations among them.

show abstract

“…is to improve the visual quality of the images. To improve the visual quality, these methods attempt to remove blocking artifacts, but original information is not guaranteed to be restored [30]. Some of them even cannot guarantee that the recovered images and the JPEG compressed images have the same QDCT coefficients and the difference between the uncompressed images and the recovered images may be even larger than that between uncompressed images and compressed images in terms of QDCT coefficients.…”

Section: Many Deblocking Methods Have Been Proposed For Generic Imagementioning

confidence: 99%

“…Some priors are imposed on some of these methods to recover the lost information. However, they are not related to biometric information [30]. In fact, many of them further deteriorate the existing information, which is already weakened by the JPEG method.…”

Section: Many Deblocking Methods Have Been Proposed For Generic Imagementioning

confidence: 99%

Restoring blood vessel patterns and tattoos from JPEG compressed skin images for forensic analysis

Li¹

View full text Add to dashboard Cite

Using digital evidence images for criminal and victim identification in some legal cases, such as child sexual abuse and masked gunman, can be very challenging, because the faces of criminals or victims are not visible. Blood vessel patterns under human skin and tattoos have been proposed as biometrics to overcome this challenge. However, these images are always taken by consumer cameras and compressed by the JPEG compression method. As a lossy compression method, the JPEG compression method seriously degrades the clarity of the blood vessel patterns and tattoos. To finally utilize blood vessels and tattoos for identifying criminals and victims or searching suspects, overcoming this challenge from the JPEG compression method is essential. Existing methods are not suitable for restoring the blood vessel patterns and tattoos because most of them are designed for generic images and their main targets are to remove the blocking artifacts and improve the visual quality. In this thesis, a skin image analysis and a compression test are performed to study the characteristics of compressed skin images. Then, based on the skin image analysis and the compression test, two skin image restoration algorithms are specially designed to restore blood vessel patterns from compressed images. Finally, an algorithm based on deep learning is proposed to recover tattoo images from their degraded versions. Skin image databases and tattoo image database are constructed for algorithm development. To recover the blood vessel patterns from compressed skin images, a skin image analysis and a compression test are first conducted to find out the critical factors influencing blood vessel pattern quality. The skin image analysis aims to figure out how blood vessel information distributes in the luminance channel (the Y channel) and the chrominance channels (the U and V channels). The compression test is further performed to identify how the lossy operations in the JPEG compression method degrade the blood vessel pattern quality. The down-sampling operation and the quantization operation are examined separately in the test. The importance of the Discrete Cosine Transform (DCT) coefficients is also tested step by step. Based on the analysis, two restoration algorithms are designed to recover blood vessel patterns by estimating the original critical DCT coefficients. I would like to thank all those people who contributed in some way to my Ph.D. study. First and foremost, I would like to express my sincere gratitude to my supervisor Dr. Kong Wai-Kin Adams for his invaluable guidance, selfless support and encouragement during my Ph.D. study. His enthusiasm and rigorous attitude to research inspire me in my study and work. He spends a lot of time and effort to train me to be an independent researcher. And he shares with me his own experience and vision about research which motivate me to reach my own goals as well. Without his guidance and persistent help this thesis would not have been possible. My sincere thanks also go to Dr. Tang Chaoying and Dr. ...

show abstract

Using a Knowledge-Based Approach to Remove Blocking Artifacts in Skin Images for Forensic Analysis

Cited by 20 publications

References 29 publications

Forensic Science Research Summary for Forgery Detection of Digital Images

Forensic Science Research Summary for Forgery Detection of Digital Images

Designing knowledge representation framework for ICD-10

Restoring blood vessel patterns and tattoos from JPEG compressed skin images for forensic analysis

Contact Info

Product

Resources

About