Learning a Deep Single Image Contrast Enhancer from Multi-Exposure Images


Aim:  To build a dataset to learn a powerful CNN-based SICE enhancer from multi-exposure
images.
Proposed system: propose to use the convolutional neural network (CNN) to train a single image contrast enhancement (SICE) enhancer. A CNN can be easily trained as the SICE enhancer to improve the contrast of an under-/over-exposure image.
Overcome: One key issue is how to construct a training data set of low-contrast and high-contrast image pairs for end-to-end CNN learning
     Advantage: 
  •  CNN based SICE method learns a complex nonlinear mapping function to map a low-contrast (either underexposure or over-exposure) region to a good contrast region. 
  •  powerful CNN-based SICE enhancer, which is capable of adaptively generating high quality enhancement result for a single over-exposed or underexposed input image.
      Existing System:  Previous SICE methods adjust the tone curve to correct the contrast of an input image. often fail in revealing image details because of the limited information in a single image. 
  •  state-of the-art SICE methods, 
  •  MEF and
  • Stack-based HDR method.
 Methodology:
a large-scale multi-exposure image dataset which contains low-contrast images with different exposure levels and their corresponding high-quality reference image. The constructed dataset makes end-to-end discriminative learning of high performance SICE methods possible. It also provides a platform to quantitatively evaluate, at least to some extent, the performance of different contrast enhancement algorithms. With the constructed dataset, a well-designed CNN is trained for SICE, which demonstrates significant advantagesover existing SICE methods. Our work provides a new solution to high performance SICE.
  CNN:
Advantage: a CNN is trained to set the parameters of bilateral filters, which are then used to enhance an input image to a desired image edited by professional photographers. Since extra information can be learned from the external dataset. As a powerful discriminative learning method, CNN has been successfully used in many low-level vision problems such as single image super-resolution [23] and image denoising [24], where a large amount of paired training samples can be generated or simulated.
SICE: aims to improve the visibility of the scene in a given single low-contrast image. It provides a way to enhance the low contrast photographs captured from a high dynamic range scene [25].
  • Advantage: the SICE method will not have such ghosting artifacts because it takes only one single exposure image as input. Due to the above reasons, SICE is more attractive and easier to implement in practice.
  •  Disadvantage:  it is much more challenging because of the limited information in a single image. Most of the previous SICE methods are based on some assumptions on high-quality images, while they may not fully exploit the information in the input image. On the other hand, the enhancement capability of existing SICE methods is rather limited due to the limited information in a single low-contrast image [9].

Future Enhancement:
Video enhancement is another important application. To apply the proposed methods to videos, we could consider enlarging our dataset and learning an LSTM (long short-term memory) based CNN enhancer to convert the conventional videos to HDR videos.

For additional details comment below with requirements.

Comments

Post a Comment

Popular posts from this blog

Secure Data Group Sharing and Dissemination with Attribute and Time Conditions in Public Cloud

Image
 Paper Synopsis: Data dissemination: Dissemination takes on the theory of the traditional view of communication, which involves a sender and receiver. The traditional communication view point is broken down into a sender sending information, and receiver collecting the information processing it and sending information back, like a telephone line. Example: Alice (owner, share)      è       Bob (view, share(with policies)) ( disseminator , re-encrypting the ciphertext) Existing system: Attribute-based encryption Attribute-based encryption (ABE) is one of new cryptographic mechanisms used in cloud to reach flexible and fine-grained secure data group sharing [4]. Especially, ciphertext-policy ABE (CP-ABE) allows data owners to encrypt data with an access policy such that only users whose attributes satisfy the access policy can decrypt the data [5]. The proxy re-encryption (PRE) scheme [7] in a manner could achieve efficient data dissemination in cloud by re-encr
Read more

Lightweight Fine-Grained Search over Encrypted Data in Fog Computing

Image
Aim: propose a Lightweight Fine-Grained Search (LFGS) system which supports fine Grained access control and single keyword search. Existing System: ·          the existing ciphertext retrieval schemes rarely focus on the fog computing environment and most of them still impose high computational and storage overhead on resource-limited end users. ·         existing CP-ABKS schemes are approximately proportional to the complexity of access policy, which greatly hinder the uses of resource-limited IoT devices. ·          existing CP-ABE schemes is that encryption or decryption operations involve time-consuming pairing operations and a number of other operations increasing with the complexity of access policy . Proposed System: Lightweight Fine-Grained ciphertexts Search (LFGS) system in fog computing by extending Ciphertext-Policy Attribute-Based Encryption (CP-ABE) and Searchable Encryption (SE) technologies, which can achieve fine-grained access control and keyword sea
Read more

A Comprehensive Study on Social Network Mental Disorders Detection via Online Social Media Mining

Image
Aim: To automatically identify SNMD patients at the early stage according to their OSN data with a novel tensor model that efficiently integrate heterogeneous data from different OSNs. Existing System: The SNMD data from different OSNs may be incomplete due to the heterogeneity (drawback) . For example, the profiles of users may be empty due to the privacy issue, different functions on different OSNs (e.g., game, check-in, event), etc.  Proposed System : propose a machine learning framework, namely, Social Network Mental Disorder Detection (SNMDD) , that exploits features extracted from social network data to accurately identify potential cases of SNMDs. The paper also exploits multi-source learning in SNMDD and propose a new SNMD-based Tensor Model (STM) to improve the accuracy.   Advantage: propose a novel tensor-based approach to address the issues of using heterogeneous data and incorporate domain knowledge in SNMD detection. Objectives: ·          to explore data m
Read more