We address the task of weakly supervised defect localization using image-level labels, which is essential for visual inspections in industrial manufacturing and infrastructure maintenance. Existing weakly supervised semantic segmentation and multiple instance learning (MIL) methods often struggle to accurately localize defects on complex structures and "in-the-wild" backgrounds. To overcome these limitations, we propose a novel MIL framework that incorporates two key innovations: residual feature learning (RFL), which highlights defect patterns by contrasting input images with reference (normal) images in the feature space, and reference image selection (RIS), which dynamically selects reference images based on similarity to enhance residual feature quality. RIS further contributes to localization performance by sampling highly similar reference images during training. We evaluate our method on the VisA and RDD2020/2022 datasets, demonstrating superior performance compared to weakly supervised semantic segmentation methods and conventional MIL-based methods in defect localization.

In this paper, we present an end-to-end domain adaptation technique that utilizes both feature distribution alignment and Self-Training effectively for object detection. One set of methods for domain adaptation relies on feature distribution alignment and adapts models on an unlabeled target domain by learning domain invariant representations through adversarial loss. Although this approach is effective, it may not be adequate or even have an adverse effect when domain shifts are large and inconsistent. Another set of methods utilizes Self-Training which relies on pseudo labels to approximate the target domain distribution directly. However, it can also have a negative impact on the model performance due to erroneous pseudo labels. To overcome these two issues, we propose to generate reliable pseudo labels through feature distribution alignment and data distillation. Further, to minimize the adverse effect of incorrect pseudo labels during Self-Training we employ interpolation-based consistency regularization called mixup. While distribution alignment helps in generating more accurate pseudo labels, mixup regularization of Self-Training reduces the adverse effect of less accurate pseudo labels. Both approaches supplement each other and achieve effective adaptation on the target domain which we demonstrate through extensive experiments on one-stage object detector. Experiment results show that our approach achieves a significant performance improvement on multiple benchmark datasets.

This paper presents a patch-based approach for crowd density estimation in public scenes. We formulate the problem of estimating density in a structured learning framework applied to random decision forests. Our approach learns the mapping between patch features and relative locations of all objects inside each patch, which contribute to generate the patch density map through Gaussian kernel density estimation. We build the forest in a coarse-to-fine manner with two split node layers, and further propose a crowdedness prior and an effective forest reduction method to improve the estimation accuracy and speed. Moreover, we introduce a semi-automatic training method to learn the estimator for a specific scene. We achieved state-of-the-art results on the public Mall dataset and UCSD dataset, and also proposed two potential applications in traffic counts and scene understanding with promising results.

This paper proposes a novel method for recognizing faces degraded by blur using deblurring of facial images. The main issue is how to infer a Point Spread Function (PSF) representing the process of blur on faces. Inferring a PSF from a single facial image is an ill-posed problem. Our method uses learned prior information derived from a training set of blurred faces to make the problem more tractable. We construct a feature space such that blurred faces degraded by the same PSF are similar to one another. We learn statistical models that represent prior knowledge of predefined PSF sets in this feature space. A query image of unknown blur is compared with each model and the closest one is selected for PSF inference. The query image is deblurred using the PSF corresponding to that model and is thus ready for recognition. Experiments on a large face database (FERET) artificially degraded by focus or motion blur show that our method substantially improves the recognition performance compared to existing methods. We also demonstrate improved performance on real blurred images on the FRGC 1.0 face database. Furthermore, we show and explain how combining the proposed facial deblur inference with the local phase quantization (LPQ) method can further enhance the performance.

This paper proposes a novel method for deblurring facial images to recognize faces degraded by blur. The main problem is how to infer a point spread function (PSF) representing the process of blur. Inferring a PSF from a single facial image is an ill-posed problem. To make this problem more tractable, our method uses learned prior information derived from a training set of blurred facial images of several individuals. We construct a feature space such that blurred faces degraded by the same PSF are similar to one another and form a cluster. During training, we compute a statistical model of each PSF cluster in this feature space. For PSF inference we compare a query image of unknown blur with each model and select the closest one. Using the PSF corresponding to that model, the query image is deblurred, ready for recognition. Experiments on a standard face database artificially degraded by focus or motion blur show that our method substantially improves the recognition performance compared with state-of-the-art methods. We also demonstrate improved performance on real blurred images.

In this paper, we propose a generic and efficient object detection framework based on two heterogeneous features and demonstrate effectiveness of our method for a cat face detection problem. Simple Haar-like features with AdaBoost are fast to compute but they are not discriminative enough to deal with complicated shape and texture. Therefore, we cascade joint Haar-like features with AdaBoost and CoHOG descriptors with a linear classifier. Since the CoHOG descriptors are extremely high dimensional pattern descriptors based on gradient orientations, they have a strong classification capability to represent various cat face patterns. The combination of these two distinct classifiers enables fast and accurate cat face detection. The experimental result with about 10,000 cat images shows that our method gives better performance in comparison with the state-of-the-art cat head detection method, although our method does not exploit any cat specific characteristics.

In this paper, we propose an efficient and generic facial feature localization method based on a weighted vector concentration approach. Our method does not require any specific priors on facial shape but implicitly learns its structural information from a training data. Unlike previous work, facial feature points are globally estimated by the concentration of directional vectors from sampling points on a face region, and those vectors are weighted by using local likelihood patterns which discriminate the appropriate position of the feature points. The directional vectors and local likelihood patterns are provided through nearest neighbor search between local patterns around the sampling points and a trained codebook of extended templates. The combination of the global vector concentration and the verification with the local likelihood patterns achieves robust facial feature point detection. We demonstrate that our method outperforms state-of-the-art method based on the Active Shape Models in our evaluation.

In this demonstration, we present a real-time “face blending” method based on an automatic detection of facial feature points. The method can blend faces of two people and generate a morphing-like synthetic image. The system is composed of a PC and a web camera. It is able to create a natural blended image from an image from the web camera in real-time. First, fourteen types of facial feature points are detected automatically in both base and texture images. Then the correspondences of the feature points and those of a 3D generic facial shape model are calculated for both images. An intermediate image whose corresponding coordinates for the model are known is generated from the texture image. Finally the blended image is rendered using the generated intermediate image and the base image.

We propose a real-time ldquoface blendingrdquo method based on an automatic detection of facial feature points. The method can blend faces of two or more people and generate a morphing-like synthetic image. The proposed method is able to create natural blended images fast. First, fourteen types of facial feature points are detected automatically in both base and texture images. Then the correspondences of the feature points and those of a 3D generic facial shape model are calculated for both images. An intermediate image whose corresponding coordinates for the model are known is generated from the texture image. Finally the blended image is rendered using the generated intermediate image and the base image. The effectiveness of the proposed method is shown through experimental results.

This paper proposes a novel method for recognizing faces in a cluster of moving people. In this task, there are two problems caused by motion, which are occlusions, and changes in facial pose and illumination. Multiple cameras are used to acquire near-frontal faces to avoid occlusions and profile faces. The hierarchical image-set matching (HISM) creates a distribution for each individual by integrating a set of face images of the same individual acquired from the multiple cameras. By adopting a method for comparing between test and training distributions in identification, variation in pose and illumination is alleviated, and good recognition accuracy can be obtained. Experimental results using video sequences containing 349 people show that the proposed method achieves high recognition performance compared with conventional methods, which use frame-by-frame identification and a distribution obtained from a single camera.

This paper proposes "Pattern Hashing" as a new scheme for object recognition by effectively introducing an appearance-based approach into the framework of a geometric feature-based approach. We compose multiple bases using a combination of arbitrary three interest points in the model object, compute the geometric invariant for similarity transformation for each basis, and apply a hash function to it. Each image patch consists of pixels which are near the basis vector. We divide the model object image into multiple partial image patches, and create various appearances on the hash table as a distributed local appearance model. In the recognition stage, fast model selection is efficiently executed by the hashing technique, and then appearance pattern matching and voting procedure extract the target object in the input image. Through experiment with a face image database, we demonstrate that partly occluded object regions or multiple object positions can indeed be detected by the proposed algorithm.

We developed a robot system which can play one-on-one volleyball games with a human player. It can not only hit a flying ball back to the player correctly but also have various autonomous functionalities to interact with humans necessary for playing games, i.e., it can pick up a ball of a requested color by recognizing voice instructions, can locate the players by recognizing their faces, and can shake hands. This robot performed the entire game sequence over 100 times at a company-sponsored exhibition, where the ball rally continued over 25 times with an arbitrary player. In this paper, we mainly describe the real-time visual feedback system of the robot which is essential for playing ball games.