Abstract
A new spatially variant smoothing filter is derived for image enhancement. The main object of this filter is to improve the output image of a linear spatially invariant image restoration filter such as Wiener filter. In this filter the processing for flat fields of image gray levels is quite different from that of edge portions of the image. As a new trial, we apply one-dimensional smoothing to the edge portions. This is because it would be important that the edge line of an image be linked smoothly for visual perception. For flat fields we divide these into three categories, 'full flat field', 'ordinary flat field', and 'less flat field'. In each field the unknown parameter of the new smoothing filter is determined optimally.
| Original language | English |
|---|---|
| Pages (from-to) | 757-762 |
| Number of pages | 6 |
| Journal | Transactions of the Institute of Electronics and Communication Engineers of Japan. Section E |
| Volume | E68 |
| Issue number | 11 |
| Publication status | Published - Nov 1985 |
| Externally published | Yes |
Fingerprint
All Science Journal Classification (ASJC) codes
- Engineering(all)
Cite this
SPATIALLY VARIANT SMOOTHING FILTER FOR IMAGE ENHANCEMENT. / Kondo, Hiroshi; Sakamoto, Hiroyasu.
In: Transactions of the Institute of Electronics and Communication Engineers of Japan. Section E, Vol. E68, No. 11, 11.1985, p. 757-762.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - SPATIALLY VARIANT SMOOTHING FILTER FOR IMAGE ENHANCEMENT.
AU - Kondo, Hiroshi
AU - Sakamoto, Hiroyasu
PY - 1985/11
Y1 - 1985/11
N2 - A new spatially variant smoothing filter is derived for image enhancement. The main object of this filter is to improve the output image of a linear spatially invariant image restoration filter such as Wiener filter. In this filter the processing for flat fields of image gray levels is quite different from that of edge portions of the image. As a new trial, we apply one-dimensional smoothing to the edge portions. This is because it would be important that the edge line of an image be linked smoothly for visual perception. For flat fields we divide these into three categories, 'full flat field', 'ordinary flat field', and 'less flat field'. In each field the unknown parameter of the new smoothing filter is determined optimally.
AB - A new spatially variant smoothing filter is derived for image enhancement. The main object of this filter is to improve the output image of a linear spatially invariant image restoration filter such as Wiener filter. In this filter the processing for flat fields of image gray levels is quite different from that of edge portions of the image. As a new trial, we apply one-dimensional smoothing to the edge portions. This is because it would be important that the edge line of an image be linked smoothly for visual perception. For flat fields we divide these into three categories, 'full flat field', 'ordinary flat field', and 'less flat field'. In each field the unknown parameter of the new smoothing filter is determined optimally.
UR - http://www.scopus.com/inward/record.url?scp=0022149914&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0022149914&partnerID=8YFLogxK
M3 - Article
VL - E68
SP - 757
EP - 762
JO - Transactions of the Institute of Electronics and Communication Engineers of Japan. Section E
JF - Transactions of the Institute of Electronics and Communication Engineers of Japan. Section E
SN - 0387-236X
IS - 11
ER -