一種用于圖像分類的語義增強(qiáng)線性編碼方法
doi: 10.11999/JEIT140743
基金項(xiàng)目:
國家自然科學(xué)基金(61175006)和博士學(xué)科點(diǎn)專項(xiàng)科研基金(20134307110029)資助課題
A Semantic Enhanced Linear Coding for Image Classification
-
摘要: 針對(duì)傳統(tǒng)編碼模型中存在的編碼歧義性問題，該文提出一種考慮特征上下文的語義增強(qiáng)線性編碼方法。首先，通過學(xué)習(xí)局部鄰域中特征共生關(guān)系矩陣來表示上下文信息。然后，在編碼過程中同時(shí)引入學(xué)習(xí)而得的上下文信息與特征上下文匹配權(quán)重得到語義增強(qiáng)編碼模型。由于上下文信息與上下文匹配權(quán)重的功能，使得此編碼方法不僅豐富了編碼的語義信息，還能夠有效避免噪聲帶來的影響。在3個(gè)基準(zhǔn)數(shù)據(jù)集(Scene15, Caltech101以及 Caltech256)上充分的實(shí)驗(yàn)驗(yàn)證了該方法的有效性。Abstract: Considering the ambiguity problem in the traditional feature coding model, a feature context-aware semantic enhanced linear coding method is proposed. At first, the context information is represented by the concurrence matrix learnt from local area of the features. Then, the context information and a context matching weight are introduced into the coding model to form a new semantic enhanced coding model. Owning to the functions of context information and the context matching weight, this model not only enriches the semantic meaning of coding, but also efficiently avoids the affects of noise. Experiments on the baselines (Scene15, Caltech101, and Caltech256) demonstrate the effectiveness of the proposed method.
-
Key words:
- Image classification /
- Feature coding /
- Context constraint /
- Ambiguity
-
計(jì)量
- 文章訪問數(shù): 1869
- HTML全文瀏覽量: 116
- PDF下載量: 717
- 被引次數(shù): 0
下載:
