The quality of finger image data is defined to be the predicted behavior of the image in a matching environment. Thus, the quality information is useful in many applications. ISO/IEC 19784-1 and ISO/IEC 19785-1 do allocate a quality field and specify the allowable range for the scores, with the recommendation that the score is divided into four categories with a qualitative interpretation for each category. Image quality fields are also provided in the fingerprint data interchange formats standardized in ISO/IEC 19794-2, ISO/IEC 19794-3, ISO/IEC 19794-4, and ISO/IEC 19794-8. However, there is no standard way to interpret the quality score that facilitates the interpretation and interchange of the finger image quality scores.
The purpose of this part of ISO/IEC 29794 is to provide an informative technical report on methodologies for objective, quantitative quality score expression and interpretation for finger images. It will complement ISO/IEC 29794-1 in developing a reference finger image corpus. Such a reference corpus can be built upon the availability of public finger images, which should then be used for quality score normalization.
For aspects of quality specific to the finger image modality, this part of ISO/IEC 29794:
- Specifies terms and definitions that are useful in the specification, use, and test of finger image quality metrics
- Defines the interpretation of finger image quality scores
- Identifies or defines finger image corpora for the purpose of serving as information for algorithm developers and users
- Develops statistical methodologies specific to finger image corpora for characterizing quality metrics to facilitate interpretation of scores and their relation to matching performance.
Performance assessment of quality algorithms and standardization of quality algorithms are outside the scope of this part of ISO/IEC 29794.
Contents of PD ISO/IEC TR 29794-4 include:- Scope
- Normative references
- Terms and definitions
- Symbols and abbreviated terms
- Finger Image Quality
- Defect factors of finger image
- Standardization approaches for exchange of finger image quality
- Finger Image Quality Analysis
- Introduction
- Local Analysis
- Constituent of Local Analysis
- Approaches to Local Analysis of Finger Image
- Global Analysis
- Constituent of Global Analysis
- Approaches to Global Analysis of Finger Image
- Unified Quality Score
- Methodology for Combining Quality Metrics
- Weighted Average
- Pattern Classifier
- Area Consideration
- Bibliography
ISO/IEC 29794 consists of the following parts, under the general title Information technology — Biometric sample quality:
Part 1: Framework
Part 4: Finger image data [Technical Report]
Part 5: Face image data [Technical Report]
