SIFT

I still have many question marks flying around my head. There may be some miss-understanding that make my implementation is weak for scaling & orientation invariance (which should be the strongest compared with the other algorithms).

Ref :

• Rob Hess
• David G. Lowe

My code is heavily base on Rob Hess`s implementation. But I don`t want to install opencv and can`t understand the descriptor building function. So I just sampling a rotated grid with fixed size in all scale. In the matching step, check distance between 2 descriptor only (accepted if d is less than 0.001)

20100223

Get better result after pre-smoothing.

新春特輯

又有兩位同事離開corel 了。然後大家超捧場的 XD

CUDA Quick Guide

春聯節

用金漆寫起來完全是兩回事！看來寫之前不能潤筆了，可那樣洗筆的時候會很難過。然後可能是顆粒比較大的關係，金粉幾乎都附在筆毛外，一筆下去就沒了，大概得多用點筆肚。

桌子很小，所以用新的螢幕接上NB，然後直接看字帖，不過這樣感覺好累啊！另外G1S的跟這台三星牌的resolution好像不太合 /_\

bug in Dragon Age

If you rush in the fade, you have to handle the same illusion twice, sometimes.

DOG

A rough DOG result between 2 scale level. (float value are clamped between 0.0f - 1.0f)

篆刻：堅

刻得很趕，刻的時候覺得狀況不太好，很久很久沒刻這麼小的章了，不過刻完後覺得效果還不錯，也就沒什麼修了。