Medical image compression using principal component analysis

Taur, J.S.; Cai, Tao

doi:10.1109/icip.1996.561051

Cited by 30 publications

(20 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In both cases, the target is to minimize the design's implementation cost and to efficiently allocate the embedded multipliers and memory blocks, if any, of the device. Face recognition/detection [2], [1], optical character recognition [3], and image compression [4] are a few of the applications where the above two problems are encountered.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…This scenario can arise in applications where the number of dimensions of the factors has to be restricted e.g. image compression [4]. From the hardware perspective, this can also be enforced due to the available memory bandwidth in the system where the factors F are stored.…”

Section: B Dimensionality Reduction Targeting a Specific Number Of Dmentioning

confidence: 99%

“…This problem is usually referred to as dimensionality reduction or feature extraction. Examples can be found in the face recognition/detection problem [1], [2] where images of people are mapped into a space with fewer dimensions than the original one capturing the main characteristics of the faces, in optical character recognition [3], in image compression [4], and others. In these examples, the objective is to capture the main modes of variation of the original data that have large impact to the overall performance of the application, and not to maintain the original information.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Exploration of Heterogeneous FPGAs for Mapping Linear Projection Designs

Bouganis

Pournara

Cheung

2010

IEEE Trans. VLSI Syst.

View full text Add to dashboard Cite

Abstract-In many applications, a reduction of the amount of the original data, or a representation of the original data by a small set of variables is often required. Among many techniques, the linear projection is often chosen due to its computational attractiveness and good performance. For applications where real-time performance and flexibility to accommodate new data are required, the linear projection is implemented in FPGAs due to their fine-grain parallelism and reconfigurability properties. Currently, the optimization of such a design is considered as a separate problem from the basis calculation leading to suboptimal solutions.In this work, we propose a novel approach that couples the calculation of the linear projection basis, the area optimization problem, and the heterogeneity exploration of modern FPGAs. The power of the proposed framework is based on the flexibility to insert information regarding the implementation requirements of the linear basis by assigning a proper prior distribution to the basis matrix. Results from real-life examples on modern FPGA devices demonstrate the effectiveness of our approach, where up to 48% reduction in the required area is achieved compared to the current approach, without any loss in the accuracy or throughput of the design.

show abstract

Section: Performance Evaluationmentioning

confidence: 99%

Section: B Dimensionality Reduction Targeting a Specific Number Of Dmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploration of Heterogeneous FPGAs for Mapping Linear Projection Designs

Bouganis

Pournara

Cheung

2010

IEEE Trans. VLSI Syst.

View full text Add to dashboard Cite

show abstract

“…For DCT, we applied 8x8 DCT matrix followed by uniform quantization of transformed components [21]. We applied PCA by extracting the principal modes of 8x8 image patches [8]. Finally, we applied vector quantization on the intensity values of centeroids of 8x8 or 16x16 blocks [18].…”

Section: Methodsmentioning

confidence: 99%

“…The lossless compression studies have all resulted in low compression rate. Transform coding schemes such as Principal Component Analysis (PCA) and Discrete Cosine Transform (DCT) were applied in [4], [8] and [9] to get better rates. In order to achieve higher compression rates without detracting from quality, region of interest based methods were investigated in the subsequent years.…”

Section: Introductionmentioning

confidence: 99%

Medical image compression based on region of interest, with application to colon CT images

Gokturk

Tomasi²,

Girod³

et al.

2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

Abstract-CT or MRI Medical imaging produce human body pictures in digital form. Since these imaging techniques produce prohibitive amounts of data, compression is necessary for storage and communication purposes. Many current compression schemes provide a very high compression rate but with considerable loss of quality. On the other hand, in some areas in medicine, it may be sufficient to maintain high image quality only in the region of interest, i.e., in diagnostically important regions. This paper discusses a hybrid model of lossless compression in the region of interest, with high-rate, motion-compensated, lossy compression in other regions. We evaluate our method on medical CT images, and show that it outperforms other common compression schemes, such as discrete cosine transform, vector quantization, and principal component analysis. In our experiments, we emphasize CT imaging of the human colon.

show abstract

Integrated information network: establishing a medical imaging diagnosis system between hospitals

Enkhjargal¹,

Lyankhtsetseg²

World Congress on Medical Physics and Biomedical Engineering 2006

View full text Add to dashboard Cite

Medical image compression using principal component analysis

Cited by 30 publications

References 5 publications

Exploration of Heterogeneous FPGAs for Mapping Linear Projection Designs

Exploration of Heterogeneous FPGAs for Mapping Linear Projection Designs

Medical image compression based on region of interest, with application to colon CT images

Integrated information network: establishing a medical imaging diagnosis system between hospitals

Contact Info

Product

Resources

About