All releases of dlib C++ Library

  •  16 Jun 2014 23:06
Avatar

    Release Notes: A bug in the way file serialization was being handled on MS Windows platforms was fixed.

    •  02 Jun 2014 23:52
    Avatar

      Release Notes: This release has been focused on minor bugfixes and usability improvements.

      •  09 Apr 2014 23:45
      Avatar

        Release Notes: The major new feature in this release is a Python API for training histogram-of-oriented-gradient based object detectors and examples showing how to use this type of detector to perform real-time face detection. Simpler interfaces were provided for learning to solve assignment and multi-target tracking problems.

        •  03 Feb 2014 23:59
        Avatar

          Release Notes: This release added a tool for training histogram-of-oriented-gradient based object detectors and examples showing how to use this type of detector to perform real-time face detection. It also added multi-threaded training options for the multiclass classifiers as well as numerous other usability improvements.

          •  22 Oct 2013 23:00
          Avatar

            Release Notes: This release adds bound constrained non-linear optimizers using the BFGS and L-BFGS methods. It also includes a new tool for learning a max-margin Mahalanobis distance metric as well as routines for easily computing Felzenszwalb's 31 channel HOG image representation.

            •  28 Aug 2013 23:09
            Avatar

              Release Notes: This release focused on improving the speed and usability of dlib's structural support vector machine solver. Two new tutorial style example programs showing how to use the solver from either C++ or Python were included.

              •  21 Jun 2013 21:50
              Avatar

                Release Notes: This release added a tool for solving large scale support vector regression problems to the library as well as a structural SVM tool for learning BIO or BILOU style sequence tagging models. It also added Python interfaces to a number of dlib's machine learning tools.

                •  31 May 2013 00:10
                Avatar

                  Release Notes: This release has primarily focused on improving the flexibility and ease of use of the object detection tools.

                  •  25 Mar 2013 22:59
                  Avatar

                    Release Notes: In addition to some bugfixes, this release also brings the following notable improvements to the library: a more accurate SURF feature extractor, a faster cutting plane solver, a routine for computing the singular value decomposition of very large matrices, a tool for performing canonical correlation analysis on large datasets, and simple tools for writing parallel for loops.

                    •  04 Feb 2013 23:34
                    Avatar

                      Release Notes: This release includes a large number of new minor features and usability improvements. It also includes a new machine learning tool for learning to rank objects. This is the dlib::svm_rank_trainer, an implementation of the well known SVM-Rank algorithm. Moreover, the implementation runs in O(n*log(n)) time and is therefore suitable for use with large training datasets.

                      Screenshot

                      Project Spotlight

                      episoder

                      A tool to tell you about new episodes of your favourite TV shows.

                      Screenshot

                      Project Spotlight

                      BalanceNG

                      A modern software IP load balancer.