Desktop version

Home arrow Engineering arrow Cellular Image Classification

Structure of the Chapters

Chapter 2 provides the reader with the fundamentals of cellular imaging, imaging feature detection and classification. We introduce the application of optical technology in imaging, and the analysis and classification of HEp-2 cell images. Our work focuses on the efficient feature extraction for staining pattern classification of HEp-2 cells. There are various features for image classification. We introduce some widely

Table 1.2 Composition of the ICIP2013 training dataset. Each table item represents the number of cells and the number of images which is in parentheses

Type

Training set

Test set

Total

Centromere

1279 (16)

1462(16)

2741 (32)

Homogeneous

1347 (16)

1147(16)

2494 (32)

Nucleolar

1273 (16)

1325 (16)

2598 (32)

Speckled

1391 (16)

1440(16)

2831 (32)

Nuclear membrane

1190(16)

1018(15)

2208 (31)

Golgi

362 (2)

362 (2)

724 (4)

Total

6842 (42)

6754 (41)

13596 (83)

used features for describing staining patterns, and some classifiers for these staining pattern classification.

In Chap. 3, we describe a low-order LP21 fiber mode for optical single cell manipulation and imaging staining patterns of HEp-2 cells. A focused four-lobed mode distribution is stable and effective in optical tweezer applications, including selective cell pick-up, pairing, grouping or separation, as well as rotation of cell dimers and clusters. Both translational dragging force and rotational torque in the experiments are in good accordance with our theoretical model. With a simple all-fiber configuration, and low peak irradiation to targeted cells, instrumentation of our optical chuck technology will provide a powerful tool in the ANA-IIF laboratories.

In Chap. 4, we introduce the Bag-of-Words (BoW) framework for image representations. Many models transform low-level descriptors into richer mid-level representations. Extracting mid-level features involves a sequence of interchangeable modules. However, they always consist of two major parts: Bag-of-Words (BoW) and Spatial Pyramid Matching (SPM). The target is to embed low-level descriptors in a representative codebook space. We introduce the key techniques employed in the BoW framework including the coding and pooling processes.

In Chap. 5, to reduce the inevitable information loss caused by coding process, we study a Linear Local Distance Coding (LLDC) method. The LLDC method transforms original local feature to more discriminative local distance vector by searching for local neighbors of the local feature in the class-specific manifolds. Then we encode and pool the local distance vectors to get salient image representation. Combined with the traditional coding methods, this method achieves higher classification accuracy.

Chapter 6 is focused on a rotation invariant textural feature of Pairwise Local Ternary Patterns with Spatial Rotation Invariant (PLTP-SRI). It is invariant to image rotations, meanwhile it is robust to noise and weak illumination. By adding spatial pyramid structure, this method captures spatial layout information. While the proposed PLTP-SRI feature extracts local feature, the BoW framework builds a global image representation.

In Chap. 7, we design a Co-occurrence Differential Texton (CoDT) feature to represent the local image patches of HEp-2 cells. The CoDT feature reduces the information loss by ignoring the quantization while it utilizes the spatial relations among the differential micro-texton feature. Thus it can increase the discriminative power. We build a generative model to adaptively characterize the CoDT feature space of the training data. Furthermore, we exploit a discriminant representation for the HEp-2 cell images based on the adaptive partitioned feature space. Therefore, the resulting representation is adapted to the classification task. By cooperating with linear Support Vector Machine (SVM) classifier, our framework can exploit the advantages of both generative and discriminative approaches for cellular image classification.

Chapter 8 concludes this monograph with its major techniques developed, and gives our perspectives on the future directions of research in this field.

 
Source
< Prev   CONTENTS   Source   Next >

Related topics