近幾年來文字檢測的研究隨著科技的進展漸漸受到關注，檢測出文字就要克服自然環境帶來的光源影響及複雜的背景這些挑戰，許多文獻提出新方法來提高辨識度，但都由於光的影響使得辨識度無法再有進一步的提升，我們這邊延續近年來學者努力的方向，利用分割顏色區域來降低複雜背景的影響，並進一步找出降低光源影響的方法，來改善文字的辨識度。
經由實驗觀察在人眼看得出同一顏色的區域中，明度不同的部份，其色度相差很小，在較看不出顏色的區域，其色度相差很大，我們這邊將此區域定義成準灰色，將看得出顏色的彩色區域分成六大類。
在彩色區塊形成後，可以找出不同顏色之間的邊緣，但在彩色區塊內的準灰色，因為色度相差很大，以至於無法正確找出邊緣，所以我們這邊提出一個新的觀念，叫做色彩強度，準灰色計算出的色彩強度很低，彩色部分的色彩強度較高，運用此特性可以找出彩色區塊內的準灰色文字。實驗結果顯示我們可以得到輪廓比較完整的邊緣檢測圖，再將這結果送進後續的SWT來提高辨識度。

Recently, researches on text detection have attracted extensive attention. There are two factors affecting text detection: non-uniform illumination and complex background. Many researches have proposed the methods to improve the precision of text detection. Due to the effects of non-uniform illumination and complex background, they can’t obtain a significant improvement. This thesis proposes a color-based text detection strategy which eliminates the effects of non-uniform illumination and complex background, resulting in improving the precision of text detection.
The region which can’t be perceived as any color easily is defined as quasi-gray region; otherwise, it is defined as color region. For quasi-gray regions, the difference of hue between pixels in the region are large. While the difference of hue between pixels in the same color region are extremely small. For the convenience of implementation, the color regions are divided into six categories: R+, R-, G+, G-, B+, and B-.
After color regions are formed, the edges between different colors can be extracted from six categories separately. However, for quasi-gray texts in the color region, many false edges may be extracted due to divergent hues in quasi-gray texts. This thesis proposes a new metric, called color-intensity. The color-intensity in the quasi-gray region is small, while the color-intensity in the color region is relatively high. Employing the color-intensity, the quasi-gray texts in the color region can be easily detected. Experiment results show that our proposed method can obtain a more accurate outline of texts, resulting in improving the precision of text detection.

[1]葉宜益, "利用局部可適性法則改良經驗模態分解法以去除不良光影," 2011.
[2]Q. Liu, C. Jung, S. Kim, Y. Moon, and J. Kim, "Stroke Filter for Text Localization in Video Images," in Image Processing, 2006 IEEE International Conference on, 2006, pp. 1473-1476.
[3]L. Jung-Jin, L. Pyoung-Hean, L. Seong-Whan, A. Yuille, and C. Koch, "AdaBoost for Text Detection in Natural Scene," in International Conference on Document Analysis and Recognition (ICDAR), 2011, 2011, pp. 429-434.
[4]J. Sochman and J. Matas, "WaldBoost - learning for time constrained sequential detection," in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. CVPR 2005. , 2005, pp. 150-156 vol. 2.
[5]R. Minetto, N. Thome, M. Cord, J. Fabrizio, and B. Marcotegui, "Snoopertext: A multiresolution system for text detection in complex visual scenes," in IEEE International Conference on Image Processing (ICIP), 2010 17th 2010, pp. 3861-3864.
[6]P. Trung Quy, P. Shivakumara, and T. Chew Lim, "Text detection in natural scenes using Gradient Vector Flow-Guided symmetry," in International Conference on Pattern Recognition (ICPR),2012 21st 2012, pp. 3296-3299.
[7]X. Wang, Y. Song, and Y. Zhang, "Natural Scene Text Detection with Multi-channel Connected Component Segmentation," pp. 1375-1379, 2013.
[8]P. Tomer and A. Goyal, "Ant clustering based text detection in natural scene images," in International Conference on Computing, Communications and Networking Technologies (ICCCNT),2013 Fourth 2013, pp. 1-7.
[9]Y. Chucai and T. YingLi, "Text Detection in Natural Scene Images by Stroke Gabor Words," in International Conference on Document Analysis and Recognition (ICDAR), 2011, 2011, pp. 177-181.
[10]A. Ikica and P. Peer, "An improved edge profile based method for text detection in images of natural scenes," in EUROCON - International Conference on Computer as a Tool (EUROCON), 2011 IEEE, 2011, pp. 1-4.
[11]P. Yi-Feng, H. Xinwen, and L. Cheng-Lin, "A Hybrid Approach to Detect and Localize Texts in Natural Scene Images," IEEE Transactions on Image Processing, vol. 20, pp. 800-813, 2011.
[12]Y. Cong, B. Xiang, L. Wenyu, M. Yi, and T. Zhuowen, "Detecting texts of arbitrary orientations in natural images," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2012 2012, pp. 1083-1090.
[13]M. Quan, S. Yonghong, Z. Yuanlin, and L. Yang, "Text detection in natural scene with edge analysis," in IEEE International Conference on Image Processing (ICIP),2013 20th 2013, pp. 4151-4155.
[14]Y. Chucai and T. YingLi, "Text String Detection From Natural Scenes by Structure-Based Partition and Grouping," IEEE Transactions on Image Processing, vol. 20, pp. 2594-2605, 2011.
[15]A. Shahab, F. Shafait, and A. Dengel, "ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images," in International Conference on Document Analysis and Recognition (ICDAR), 2011 2011, pp. 1491-1496.