Implementation of Gabor filter to texture analysis of radiographs in the assessment of osteoporosis

Multi-channel filtering implemented using the Gabor function, or Gabor filter, is capable of mimicking characteristics of the human visual system. In the assessment of osteoporosis, Gabor filter is used to calculate features from a trabecular pattern recorded on radiographs of a proximal femur. The assessment of osteoporosis can be done by observing and analyzing the trabecular pattern in the proximal femur. The feature extraction method used is energy calculation. The energy then is used for assessment or classification. The predetermined Singh index of the trabecular pattern is used to justify the classification result.