http://hdl.handle.net/10204/909 2013-05-24T01:44:24Z 2013-05-24T01:44:24Z Baumbach, J http://hdl.handle.net/10204/6520 2013-02-04T21:55:21Z 2012-07-01T00:00:00Z

Title: Colour and camouflage: design issues in military clothing Authors: Baumbach, J Abstract: Camouflage, the art of going (as long as possible) undetected by an observer, has changed over the last decade to become a discipline with a more scientific and analytical foundation. Design of a camouflage system needs to consider the capabilities of the human as an observer (on both physiological and psychophysical levels.) Description: Copyright: Woodhead Publishing,Cambridge,UK

2012-07-01T00:00:00Z Cronje, J De Villiers, J http://hdl.handle.net/10204/6502 2013-01-31T21:55:15Z 2012-11-01T00:00:00Z

Title: A comparison of image features for registering LWIR and visual images Authors: Cronje, J; De Villiers, J Abstract: This paper presents a comparison of several established and recent image feature-descriptors to register long wave infra-red images in the 8–14 m band to visual band images. The feature descriptors were chosen to include robust algorithms, SURF and SIFT — and fast algorithms, BRISK and BFROST. To evaluate the feature-descriptors a ground truth was created by determining the intrinsic and extrinsic camera calibration parameters for the cameras and using this to photogrammetrically relate pixel positions between the images. The inlier results of each feature descriptor for the top 20%, 50% and 100% of the matches (based on match strength) were used to create a homography. The average pixel error between the homography reprojected feature points and the photogrammetric reprojection was used as the error. The results show that none of the descriptors perform well in standard form, with BFROST faring slightly better than the other algorithms. This suggests a need to modify the algorithms to detect physical/structural features and de-emphasise textural features. Description: 23rd Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), Pretoria, South Africa, 29-30 November 2012

2012-11-01T00:00:00Z Cronje, J De Villiers, J http://hdl.handle.net/10204/6484 2013-01-28T21:55:28Z 2012-11-01T00:00:00Z

Title: A comparison of image features for registering LWIR and visual images Authors: Cronje, J; De Villiers, J Abstract: This paper presents a comparison of several established and recent image feature-descriptors to register long wave infra-red images in the 8–14 m band to visual band images. The feature descriptors were chosen to include robust algorithms, SURF and SIFT — and fast algorithms, BRISK and BFROST. To evaluate the feature-descriptors a ground truth was created by determining the intrinsic and extrinsic camera calibration parameters for the cameras and using this to photogrammetrically relate pixel positions between the images. The inlier results of each feature descriptor for the top 20%, 50% and 100% of the matches (based on match strength) were used to create a homography. The average pixel error between the homography reprojected feature points and the photogrammetric reprojection was used as the error. The results show that none of the descriptors perform well in standard form, with BFROST faring slightly better than the other algorithms. This suggests a need to modify the algorithms to detect physical/structural features and de-emphasise textural features. Description: 23rd Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), Pretoria, South Africa, 29-30 November 2012. Published in PRASA 2012.

2012-11-01T00:00:00Z Cronje, J http://hdl.handle.net/10204/6464 2013-01-28T21:56:15Z 2012-11-01T00:00:00Z

Title: Figure detection and part label extraction from patent drawing images Authors: Cronje, J Abstract: The US Patent and Trademark Office, together with the NASA Tournament Lab, launched a contest to develop specialized algorithms to help bring the seven million patents presently in the patent archive into the digital age. The contest was hosted by TopCoder.com, the largest competitive online software developer community. The challenge was to detect, segment and recognize figures, captions and part labels from patent drawing images. The solution presented in this work was the winning submission. Description: 23rd Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), Pretoria, South Africa, 29-30 November 2012

2012-11-01T00:00:00Z