SOLICITATION NOTICE
R -- JPEG2000 Capabilities for Hybrid Vector Scalar Quantization (HVSQ) Compression for Multiple Image Classes
- Notice Date
- 7/7/2005
- Notice Type
- Solicitation Notice
- NAICS
- 519190
— All Other Information Services
- Contracting Office
- Department of Health and Human Services, National Institutes of Health, National Library of Medicine, 8600 Rockville Pike, Bethesda, MD, 20894
- ZIP Code
- 20894
- Solicitation Number
- 05-144-CYC
- Response Due
- 7/22/2005
- Archive Date
- 8/6/2005
- Description
- It is the intent of the National Library of Medicine (NLM) to procure professional services from Texas Tech University, Lubbock, Texas (Dr. Sundnda Mitra) on a sole source basis. Period of Performance: September 1, 2005 - August 31, 2006. Professional services of experts in image compression, image segmentation of uterine cervix images by deterministic annealing, morphology, and clustering, and software development tools are required to support ongoing research into designing a Web-based digital archive for disseminating high-quality cervix images for critical evaluation by biomedical specialists worldwide. Task description: Subtask 1: Extend the HVSQ algorithm to incorporate all JPEG2000-like capabilities described in the Proposed Work section, including capability to operate efficiently on large images by random access to rectangular subimages and varying resolution levels. Test the algorithm on spine x-ray images, uterine cervix cervicography images, and histology images provided by the government. Subtask 2: Extend the HVSQ algorithm to incorporate client/server capability for Web operation and to conform to Internet Imaging Protocol (IIP). Test the algorithm by interfacing it with a publicly available IIP server and client to deliver image data efficiently from HVSQ-compressed images over the Web. Subtask 3: Extend segmentation methods previously developed for uterine cervicography for segmentation of acetowhitened regions and identification of mosaicicm in small numbers of high visual quality images to operate robustly across a broader ranger of images with lower visual quality with respect to illumination and viewing angle, and to identify punctuation, vasculature, and other biomarkers commonly used by oncological gynecologists to identify pre-cancer in uterine cervicographs. Subtask 4: Evaluate the implemented segmentation methods on a training/test set of uterine cervix images provided by the government. For subtask 4, the Contractor will be provided with a number of uterine cervix images with acetowhite and other regions of interests manually segmented by medical experts for evaluating the performance of the automated segmentation algorithms. Evaluation criteria for contract award: (1) The investigator shall have at least 10 years experience at a senior research level in the fields of image compression and image segmentation that shall include published expertise in the specialties of vector and scalar quantization, hybrid compression methods, wavelet compression, segmentation of grayscale and color images, color space transforms, application of clustering techniques to segmentation problems, and shall have published expertise in the use of these compression and segmentation techniques to the specific domains of biomedical images consisting of digitized spine x-rays and digitized 35 mm color slides of the uterine cervix. (2) The investigator shall have specific expertise in the HMVQ technique previously applied to the compression/decompression of spine x-ray images. (3) The investigator shall have specific expertise in the development of an advanced technique such as HVSQ that incorporates but improves upon the HMVQ approach for compression/decompression of both spine x-ray images and uterine cervix images. Texas Tech University is uniquely qualified for this work because of the expertise and experience of the principal investigator below (Dr. Mitra) in the specific areas of Hybrid Vector-Scalar Quantization (HVSQ) and Hybrid Multi-scale Vector Quantization (HMVQ) design for compression/decompression of digitized spine x-rays, and its extension to digitized color cervix images combined with her extensive educational background and research experience in advanced image processing [5-7,11-17], including segmentation of National Cancer Institute uterine cervix images, and numerous other technical publications, and the support of the facilities and staff of the Texas Tech Computer Vision and Image Analysis Laboratory (CVIAL). The co- investigator Dr. Brian Nutter's strong background in image processing and designing network protocol provides complementary support to this work. The co-investigators Dr. Karp and Dr. Yang will provide significant support to this work due to their strong background in wavelet based coding. Dr. Yang 's extensive experience in image coding and segmentation is crucial to this work. The proposed acquisition will be procured under FAR Part 13 - Acquisitions of Non- Commercial Items. This is not a Request for Quotations (RFQ), nor is an RFQ available. However, all responsive sources may submit a capabilities statement in a timely manner that will be considered by the Government. Sources interested in responding to this notice must be able to provide convincing evidence that they possess the requisite expertise and experience to successfully perform the services as specified above. Responses must be in writing and must be received in the office within fifteen (15) business days from the publication date of this notice. Proposals must include pricing information. NLM Synopsis No. NLM 05-144/CYC. Inquires regarding this procurement may be made to Cara Y. Calimano, Contract Specialist, NLM on (301) 496-6127.
- Place of Performance
- Address: 8600 Rockville Pike, Bethesda, Maryland
- Zip Code: 20894
- Country: USA
- Zip Code: 20894
- Record
- SN00842796-W 20050709/050707211828 (fbodaily.com)
- Source
-
FedBizOpps.gov Link to This Notice
(may not be valid after Archive Date)
| FSG Index | This Issue's Index | Today's FBO Daily Index Page |