思在樹人

以前寫了一篇論文摘要的寫法（http://hjlee0301.pixnet.net/blog/post/8951308），想不到它還是我文章中的人氣王，看起來不少人有這方面的需求，今天就拿我目前正在看的幾篇期刊論文來分析一下，這些文章有四篇是發表在IEEE的期刊。另請注意的是這裡的寫法比較適合以提出方法為主的科技論文。

論文一：

In face recognition tasks, the dimension of the sample space is typically larger than the number of the samples in the training set. As a consequence, the within-class scatter matrix is singular and the Linear Discriminant Analysis (LDA) method cannot be applied directly. This problem is known as the "small sample size" problem. 背景（B）這五篇文章中就只有這一篇交代背景。

In this paper, we propose a new face recognition method called the Discriminative Common Vector method based on a variation of Fisher's Linear Discriminant Analysis for the small sample size case. 目的/主要工作（P）

Two different algorithms are given to extract the discriminative common vectors representing each person in the training set of the face database. One algorithm uses the within-class scatter matrix of the samples in the training set while the other uses the subspace methods and the Gram-Schmidt orthogonalization procedure to obtain the discriminative common vectors. Then, the discriminative common vectors are used for classification of new faces. 方法（M）

The proposed method yields an optimal solution for maximizing the modified Fisher’s Linear Discriminant criterion given in the paper. 結果（R）

Our test results show that the Discriminative Common Vector method is superior to other methods in terms of recognition accuracy, efficiency, and numerical stability.結論（C）

這一篇論文摘要的結構和論文寫作書本講解的最契合。另外請注意英文時態的用法，這篇論文用的幾乎都是現在式，下面四篇也都是這樣；有些論文寫作的書會建議：目的、方法和結果使用過去式，這在以實驗結果的解釋/發現為主題的論文中應該是主流，我要建議的是：去找幾篇你要投稿期刊中的文章來分析。

 

論文二：

We consider the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise. 目的（P），開宗明義就提出論文的目的，很多人喜歡這樣寫，後面這四篇論文都是這樣起頭的。

We cast the recognition problem as one of classifying among multiple linear regression models and argue that new theory from sparse signal representation offers the key to addressing this problem. Based on a sparse representation computed by 1-minimization, we propose a general classification algorithm for (image-based) object recognition. 方法（M）

This new framework provides new insights into two crucial issues in face recognition: feature extraction and robustness to occlusion. For feature extraction, we show that if sparsity in the recognition problem is properly harnessed, the choice of features is no longer critical. What is critical, however, is whether the number of features is sufficiently large and whether the sparse representation is correctly computed. Unconventional features such as downsampled images and random projections perform just as well as conventional features such as Eigenfaces and Laplacianfaces, as long as the dimension of the feature space surpasses certain threshold, predicted by the theory of sparse representation. This framework can handle errors due to occlusion and corruption uniformly by exploiting the fact that these errors are often sparse with respect to the standard (pixel) basis. 結果（R）

The theory of sparse representation helps predict how much occlusion the recognition algorithm can handle and how to choose the training images to maximize robustness to occlusion. We conduct extensive experiments on publicly available databases to verify the efficacy of the proposed algorithm and corroborate the above claims. 結論（C）

這篇論文摘要裡面對方法的描述很簡略，對方法所達到的結果用質性的方法來描述，篇幅相對的比較長。 

論文三：

This paper presents a theoretically very simple, yet efficient, multiresolution approach to gray-scale and rotation invariant texture classification based on local binary patterns and nonparametric discrimination of sample and prototype distributions. 目的/主要工作（P）

The method is based on recognizing that certain local binary patterns, termed uniform, are fundamental properties of local image texture and their occurrence histogram is proven to be a very powerful texture feature. We derive a generalized gray-scale and rotation invariant operator presentation that allows for detecting the uniform patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis. 方法（M）

The proposed approach is very robust in terms of gray-scale variations since the operator is, by definition, invariant against any monotonic transformation of the gray scale. 結果1（R）

Another advantage is computational simplicity as the operator can be realized with a few operations in a small neighborhood and a lookup table. 結果2（R）

Excellent experimental results obtained in true problems of rotation invariance, where the classifier is trained at one particular rotation angle and tested with samples from other rotation angles, demonstrate that good discrimination can be achieved with the occurrence statistics of simple rotation invariant local binary patterns. 結果3（R）

These operators characterize the spatial configuration of local image texture and the performance can be further improved by combining them with rotation invariant variance measures that characterize the contrast of local image texture. 結論1（C）

The joint distributions of these orthogonal measures are shown to be very powerful tools for rotation invariant texture analysis. 結論2（C）

這篇論文摘要的結果部分，前兩者在講優點。 

論文四：

This paper presents a new two-stage multi-view framework for the analysis of human interactions and activities. 目的（P）

The analysis is performed in a distributed multi-view vision system that synergistically integrates track- and body-level processing. The proposed framework is geared toward versatile and easily-deployable systems that do not require careful camera calibration. 方法（M）

The main contributions of the paper are as follows; (1) context-dependent view switching for occlusion handling, (2) a method for switching the two-stage analysis between the track- and body-level processing, and (3) a hypothesis–verification paradigm for top-down feedback that exploits the spatio-temporal constraints inherent in human interaction. 結果（R）─以貢獻的描述為主，和前一篇講優點意思類似。

An experimental evaluation shows the efficacy of the proposed system for analyzing multi-person interactions. 結論（C）

這篇摘要比較短，有的期刊有長度限制。

 

論文五：

This paper proposes a novel high-order local pattern descriptor, local derivative pattern (LDP), for face recognition. 目的（P）

LDP is a general framework to encode directional pattern features based on local derivative variations. 背景（B）

The nth-order LDP is proposed to encode the (n - 1) -order local derivative direction variations, which can capture more detailed information than the first-order local pattern used in local binary pattern (LBP). Different from LBP encoding the relationship between the central point and its neighbors, the LDP templates extract high-order local information by encoding various distinctive spatial relationships contained in a given local region. 方法（M）

Both gray-level images and Gabor feature images are used to evaluate the comparative performances of LDP and LBP. Extensive experimental results on FERET, CAS-PEAL, CMU-PIE, Extended Yale B, and FRGC databases show that the high-order LDP consistently performs much better than LBP for both face identification and face verification under various conditions. 結果（R）＋ 結論（C）

這篇論文的摘要中背景寫在目的後面面，背景的交代比較像在為題目的主角作進一步的說明；實驗進行方法用一個句子交代，結果和結論又用另一句蠻長的句子來交代。

分析完了這五篇論文的摘要，我建議大家熟悉一下第一篇的表達方式，然後根據你論文的特性加以調整。